INDEX

Explanations

mentions of organizations or entities related to informed analysis and policy-making

oai_token-act-pair · gpt-3.5-turbo

references to "think tanks" and the concept of thinking

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

EStreamFrame

-0.73

anca

-0.73

 tears

-0.66

Merit

-0.63

 heels

-0.62

theless

-0.62

 Peninsula

-0.61

eding

-0.61

anie

-0.59

ances

-0.58

POSITIVE LOGITS

tank

0.86

 aloud

0.81

 differently

0.80

dress

0.77

lessly

0.76

orial

0.76

 provoking

0.75

speak

0.74

 critically

0.73

 about

0.73

Activations Density 0.067%

mentions of organizations or entities related to informed analysis and policy-making

references to "think tanks" and the concept of thinking

No Known Activations