INDEX

Explanations

references to the word "Prison" or related terms in a text

oai_token-act-pair · gpt-3.5-turbo

references to the term "Prison" and related concepts involving regulation or pricing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 deed

-0.86

lihood

-0.70

 mound

-0.70

 frag

-0.70

wip

-0.68

mens

-0.68

sound

-0.67

 loud

-0.66

 lender

-0.65

manship

-0.64

POSITIVE LOGITS

Pr

1.11

ison

0.94

ices

0.91

inson

0.88

ests

0.83

ax

0.82

anty

0.82

zn

0.80

Avg

0.79

andra

0.79

Activations Density 0.007%

references to the word "Prison" or related terms in a text

references to the term "Prison" and related concepts involving regulation or pricing

No Comments

No Known Activations