INDEX

Explanations

mentions of nerve-related terms

oai_token-act-pair · gpt-3.5-turbo

references to nerve-related concepts and their implications

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

laws

-0.89

atchewan

-0.79

aneers

-0.78

enhagen

-0.78

tions

-0.76

ioch

-0.73

eanor

-0.71

night

-0.70

enance

-0.70

iesta

-0.70

POSITIVE LOGITS

 nerve

1.14

 endings

1.02

 nerves

0.85

 pier

0.81

voy

0.79

 fibers

0.79

gas

0.75

fib

0.75

 Stim

0.74

 stim

0.73

Activations Density 0.017%

mentions of nerve-related terms

references to nerve-related concepts and their implications

No Comments

No Known Activations