INDEX

Explanations

phrases related to holding individuals or groups accountable

oai_token-act-pair · gpt-3.5-turbo

references to specific events or actions related to advocacy and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

)=(

-0.62

 Canaver

-0.59

etheless

-0.56

 archived

-0.52

 summed

-0.50

awaru

-0.49

 historian

-0.49

 Trace

-0.46

 angled

-0.46

 heterogeneity

-0.46

POSITIVE LOGITS

pers

0.62

vers

0.60

.",

0.59

adium

0.58

ankind

0.57

?",

0.56

verage

0.56

lees

0.55

nels

0.54

xia

0.54

Activations Density 1.311%

phrases related to holding individuals or groups accountable

references to specific events or actions related to advocacy and social issues

No Comments

No Known Activations