INDEX

Explanations

words related to influential figures or entities

oai_token-act-pair · gpt-3.5-turbo

references to influential individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

gged

-0.76

thia

-0.76

otide

-0.75

ft

-0.74

È

-0.74

ago

-0.73

á

-0.73

few

-0.72

AUT

-0.71

thus

-0.71

POSITIVE LOGITS

 influential

0.96

 endorsements

0.86

 influ

0.85

 personalities

0.83

 influence

0.81

 clout

0.80

 figures

0.73

 voices

0.73

ãĤ¼ãĤ¦ãĤ¹

0.71

 enough

0.70

Activations Density 0.013%

words related to influential figures or entities

references to influential individuals or entities

No Comments

No Known Activations