INDEX

Explanations

mentions of specific names or entities in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to individuals involved in personal experiences or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

allery

-0.43

 Romeo

-0.43

 danced

-0.43

arnaev

-0.42

uably

-0.42

 lasted

-0.41

 furthermore

-0.41

 Mehran

-0.40

enegger

-0.40

ãĥ¼ãĥĨãĤ£

-0.40

POSITIVE LOGITS

sw

0.41

iasm

0.40

min

0.39

 CONTR

0.38

 vantage

0.37

chem

0.37

ackets

0.37

 margins

0.37

arent

0.36

 depths

0.34

Activations Density 5.297%

mentions of specific names or entities in various contexts

references to individuals involved in personal experiences or actions

No Comments

No Known Activations