INDEX

Explanations

numerical codes or identifiers embedded in the text

oai_token-act-pair · gpt-3.5-turbo

numerical values, specifically model or component identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 snowball

-0.76

 Oath

-0.66

querque

-0.65

ggies

-0.62

ogene

-0.60

 plateau

-0.60

iri

-0.60

unia

-0.60

 Yelp

-0.60

ifully

-0.60

POSITIVE LOGITS

DM

0.86

CAP

0.86

XX

0.86

CB

0.82

XXX

0.81

VB

0.81

0.80

DX

0.80

0.79

Activations Density 0.099%

numerical codes or identifiers embedded in the text

numerical values, specifically model or component identifiers

No Comments

No Known Activations