INDEX

Explanations

words related to insecurity and self-esteem

oai_token-act-pair · gpt-3.5-turbo

terms related to insecurity and self-esteem issues

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

ague

-0.92

endez

-0.75

 footsteps

-0.70

advertising

-0.69

estone

-0.67

eree

-0.66

ICA

-0.66

NetMessage

-0.66

dule

-0.63

ell

-0.63

POSITIVE LOGITS

 insecurity

0.91

 insecure

0.87

 comprom

0.81

aged

0.77

 masculinity

0.76

framework

0.72

urated

0.71

 quot

0.71

riad

0.70

 adolesc

0.70

Activations Density 0.008%

words related to insecurity and self-esteem

terms related to insecurity and self-esteem issues

No Comments

No Known Activations