INDEX

Explanations

phrases related to government actions and decision-making

oai_token-act-pair · gpt-3.5-turbo

mentions of government officials and their actions

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

maxwell

-0.86

.)

-0.79

+.

-0.77

Todd

-0.75

 Boone

-0.75

 Slate

-0.73

 Whitman

-0.72

 Shelby

-0.72

enton

-0.71

 Everett

-0.69

POSITIVE LOGITS

 Azerbaijan

0.91

 Azerbai

0.90

 envis

0.88

NGO

0.86

 Daesh

0.86

 NGOs

0.86

 organisations

0.85

Â´

0.84

 belonging

0.83

 Regarding

0.83

Activations Density 0.815%

phrases related to government actions and decision-making

mentions of government officials and their actions

No Comments

No Known Activations

phrases related to government actions and decision-making

mentions of government officials and their actions

No Comments

No Known Activations