INDEX

Explanations

mentions of legal or diplomatic immunity

oai_token-act-pair · gpt-3.5-turbo

terms related to legal immunity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

oric

-0.82

furt

-0.80

straight

-0.73

colo

-0.73

tail

-0.73

geist

-0.73

urgical

-0.71

Ctrl

-0.71

rament

-0.69

rum

-0.68

POSITIVE LOGITS

 immunity

1.20

 afforded

0.94

ionage

0.83

 lapse

0.81

 pardon

0.79

 granted

0.77

 pard

0.76

 Immunity

0.72

 amnesty

0.71

 subpoena

0.71

Activations Density 0.029%

mentions of legal or diplomatic immunity

terms related to legal immunity

No Comments

No Known Activations