INDEX

Explanations

mentions of criminal convictions

oai_token-act-pair · gpt-3.5-turbo

references to legal convictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ffee

-0.64

 Remastered

-0.63

idge

-0.63

arov

-0.63

mentation

-0.60

sie

-0.59

gm

-0.59

estamp

-0.58

Management

-0.58

arity

-0.58

POSITIVE LOGITS

 felon

1.20

 convict

1.04

 guilty

1.03

fel

0.90

 sentenced

0.89

 unfocusedRange

0.89

 rapist

0.86

 contempt

0.85

 verdict

0.84

 convicted

0.83

Activations Density 0.039%

mentions of criminal convictions

references to legal convictions

No Comments

No Known Activations