INDEX

Explanations

words related to weakness or vulnerability

oai_token-act-pair · gpt-3.5-turbo

instances of the word "weak" and related concepts of weakness

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

 Andromeda

-0.72

 Noir

-0.72

agher

-0.71

ICAN

-0.69

 McCann

-0.68

andise

-0.68

akeru

-0.68

pheus

-0.67

ilon

-0.66

alogue

-0.66

POSITIVE LOGITS

nesses

1.29

lings

1.19

ling

1.06

ens

0.98

ening

0.96

ener

0.94

est

0.93

ened

0.93

ly

0.91

les

0.90

Activations Density 0.024%

words related to weakness or vulnerability

instances of the word "weak" and related concepts of weakness

No Comments

No Known Activations