INDEX

Explanations

words related to negative or harmful situations or conditions

oai_token-act-pair · gpt-3.5-turbo

references to unwanted or unwelcome experiences and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lass

-0.87

hetti

-0.83

mberg

-0.82

mun

-0.81

alach

-0.81

ysics

-0.80

opsy

-0.80

sis

-0.79

urgy

-0.78

oan

-0.78

POSITIVE LOGITS

 unwanted

1.32

 pregnancies

1.17

 pregnancy

0.94

ãĤī

0.87

 unwelcome

0.83

 Parenthood

0.82

 Jagu

0.80

 adolesc

0.78

 indisc

0.75

 offspring

0.72

Activations Density 0.007%

words related to negative or harmful situations or conditions

references to unwanted or unwelcome experiences and situations

No Comments

No Known Activations