INDEX

Explanations

words related to statements or opinions

oai_token-act-pair · gpt-3.5-turbo

statements or assertions made by advocates or officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Himself

-0.94

ï¸

-0.70

ascript

-0.67

à¦

-0.65

SourceFile

-0.65

Lex

-0.65

crow

-0.65

ufact

-0.64

artist

-0.63

icut

-0.63

POSITIVE LOGITS

 they

0.99

 majorities

0.71

 there

0.70

 theirs

0.69

 otherwise

0.69

 goodbye

0.67

it

0.64

 that

0.64

 alike

0.63

 loopholes

0.63

Activations Density 0.156%

words related to statements or opinions

statements or assertions made by advocates or officials

No Comments

No Known Activations