INDEX

Explanations

references to political figures, specifically senators

oai_token-act-pair · gpt-3.5-turbo

mentions of senators

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

tera

-0.64

ãĥ¼ãĥ³

-0.64

Company

-0.63

footed

-0.62

aster

-0.60

iHUD

-0.60

 Siberian

-0.60

Ø§ÙĦ

-0.60

phal

-0.59

 upkeep

-0.59

POSITIVE LOGITS

iors

1.00

ileaks

0.92

pai

0.92

arians

0.89

ial

0.88

eca

0.84

ially

0.81

hips

0.78

 Dianne

0.78

ials

0.77

Activations Density 0.018%

references to political figures, specifically senators

mentions of senators

No Comments

No Known Activations