INDEX

Explanations

phrases related to extreme or negative situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "worst" to highlight negative situations or conditions

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

agine

-0.81

raltar

-0.80

sure

-0.78

trl

-0.74

dinand

-0.73

andise

-0.73

uador

-0.72

itialized

-0.70

bold

-0.70

leans

-0.69

POSITIVE LOGITS

 offender

1.00

 imaginable

0.96

 offenders

0.94

 nightmare

0.93

 behaved

0.83

 nightmares

0.77

 losers

0.75

 possible

0.75

liest

0.74

 loser

0.73

Activations Density 0.022%

phrases related to extreme or negative situations

instances of the word "worst" to highlight negative situations or conditions

No Comments

No Known Activations