INDEX

Explanations

words related to agreement or consensus

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consensus or agreement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ener

-0.79

udi

-0.78

gallery

-0.75

 Laksh

-0.70

 Lans

-0.66

 predators

-0.65

 Hutch

-0.64

Mae

-0.64

interrupted

-0.64

 Uriel

-0.63

POSITIVE LOGITS

 unanimously

0.87

 terms

0.83

 disagree

0.78

LY

0.76

 agreeing

0.74

 principle

0.71

 hugs

0.69

 consensus

0.67

heartedly

0.66

ä¹

0.65

Activations Density 0.154%

words related to agreement or consensus

phrases indicating consensus or agreement

No Comments

No Known Activations