INDEX

Explanations

phrases indicating high probability or likelihood of something happening

oai_token-act-pair · gpt-3.5-turbo

phrases that express certainty or likelihood

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

noticed

-0.60

 painter

-0.59

 upstream

-0.59

ò

-0.58

heast

-0.58

oran

-0.58

Bul

-0.57

Fuj

-0.56

sensitive

-0.56

Rox

-0.55

POSITIVE LOGITS

be

0.98

 derive

0.80

idate

0.77

 satisfy

0.77

LECT

0.75

ect

0.75

loo

0.74

 omit

0.73

 generate

0.72

owe

0.72

Activations Density 0.050%

phrases indicating high probability or likelihood of something happening

phrases that express certainty or likelihood

No Comments

No Known Activations