INDEX

Explanations

organizations, groups, and movements with a focus on taking action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Action" and related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yth

-0.88

gling

-0.75

artifacts

-0.75

achy

-0.72

yton

-0.72

ĨĴ

-0.72

aves

-0.72

gow

-0.71

Ħ¢

-0.71

agar

-0.69

POSITIVE LOGITS

 Replay

0.98

Aid

0.78

 Fund

0.77

 Coordinator

0.77

 Committees

0.76

 Plan

0.76

 Agency

0.76

 Assistance

0.76

 Desk

0.75

tec

0.75

Activations Density 0.018%

organizations, groups, and movements with a focus on taking action

occurrences of the word "Action" and related phrases

No Comments

No Known Activations