INDEX

Explanations

words related to specific places or entities, specifically those with the pattern "Sou" or "Sask"

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orate

-0.79

urate

-0.73

 hist

-0.69

ipolar

-0.67

uate

-0.65

oard

-0.65

jamin

-0.64

umen

-0.64

arding

-0.63

 withholding

-0.63

POSITIVE LOGITS

plings

0.87

atchewan

0.79

 Rough

0.78

crow

0.77

ustain

0.77

atoon

0.76

stice

0.75

udo

0.75

pling

0.74

zhen

0.74

Activations Density 0.085%

words related to specific places or entities, specifically those with the pattern "Sou__" or "Sask__"

references to specific geographic locations and organizations

No Comments

No Known Activations

words related to specific places or entities, specifically those with the pattern "Sou" or "Sask"