INDEX

Explanations

mentions of former individuals in various professional or political roles

oai_token-act-pair · gpt-3.5-turbo

references to former individuals or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 push

-0.68

 prints

-0.68

 sequences

-0.67

 rush

-0.64

 console

-0.63

 work

-0.63

 digit

-0.63

 catalog

-0.62

ry

-0.61

 sequencing

-0.61

POSITIVE LOGITS

Former

3.48

 Former

2.52

former

1.83

 former

1.72

formerly

1.45

Senior

1.30

Veter

1.22

Actor

1.19

Executive

1.17

Attorney

1.15

Activations Density 0.016%

mentions of former individuals in various professional or political roles

references to former individuals or positions

No Comments

No Known Activations