INDEX

Explanations

phrases related to authors contributing to news reports

oai_token-act-pair · gpt-3.5-turbo

references to contributions by news organizations or journalists

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mods

-0.72

Īè

-0.72

é¾įå¥ĳå£«

-0.71

 Majesty

-0.70

 damned

-0.68

Ws

-0.67

 seams

-0.66

Rs

-0.64

 pits

-0.62

 predators

-0.62

POSITIVE LOGITS

otation

0.84

inion

0.78

rolet

0.74

imore

0.71

enhagen

0.70

 contributed

0.68

 editorial

0.68

endum

0.66

enum

0.65

alysed

0.64

Activations Density 0.147%

phrases related to authors contributing to news reports

references to contributions by news organizations or journalists

No Comments

No Known Activations