INDEX

Explanations

mentions of whistleblowers and actions related to whistleblowing

oai_token-act-pair · gpt-3.5-turbo

phrases related to whistleblowing and related acts of exposing wrongdoing

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

itates

-0.95

itated

-0.93

itate

-0.88

itating

-0.82

icular

-0.79

anian

-0.75

usa

-0.73

izable

-0.70

hetical

-0.66

imus

-0.65

POSITIVE LOGITS

 whistle

1.03

oshenko

0.88

 blowing

0.86

 informant

0.85

dropping

0.83

bley

0.79

 whistleblower

0.78

stakes

0.78

 leak

0.78

 secrecy

0.77

Activations Density 0.132%

mentions of whistleblowers and actions related to whistleblowing

phrases related to whistleblowing and related acts of exposing wrongdoing

No Known Activations