INDEX

Explanations

words related to divisions or distinctions between different groups or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to divisions or gaps between groups or concepts

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

oken

-0.80

leeve

-0.76

vez

-0.73

OD

-0.72

elin

-0.70

psc

-0.70

undai

-0.68

agara

-0.67

elta

-0.63

zin

-0.62

POSITIVE LOGITS

naire

0.89

 divides

0.80

 divide

0.77

 between

0.76

 pits

0.76

 dividing

0.71

 separating

0.70

 Divide

0.70

 Beir

0.69

wid

0.69

Activations Density 0.026%

words related to divisions or distinctions between different groups or entities

terms related to divisions or gaps between groups or concepts

No Comments

No Known Activations