INDEX

Explanations

mentions of personal or shared experiences

oai_token-act-pair · gpt-3.5-turbo

references to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

yright

-0.83

vous

-0.80

utm

-0.75

corn

-0.74

odynam

-0.71

nod

-0.70

efficiency

-0.69

trap

-0.69

emort

-0.69

iff

-0.69

POSITIVE LOGITS

 firsthand

0.92

 experiences

0.88

 experien

0.83

ually

0.79

 taught

0.79

 Exper

0.77

 abroad

0.75

 gained

0.73

 teaches

0.73

ional

0.71

Activations Density 0.037%

mentions of personal or shared experiences

references to personal experiences

No Comments

No Known Activations