INDEX

Explanations

the names of cities, people, and companies

oai_token-act-pair · gpt-3.5-turbo

proper nouns referring to geographic locations and sports teams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ensional

-0.54

 hindsight

-0.47

\/\/

-0.46

Reviewer

-0.45

 unfavorable

-0.45

ratom

-0.44

Ö¼

-0.44

 withd

-0.43

minist

-0.43

imilar

-0.43

POSITIVE LOGITS

etc

0.98

 respectively

0.65

TBA

0.64

etc

0.61

srf

0.55

};

0.53

 thereof

0.52

 Tone

0.50

ĪĴ

0.50

Activations Density 0.580%

the names of cities, people, and companies

proper nouns referring to geographic locations and sports teams

No Comments

No Known Activations