INDEX

Explanations

laws or legal acts

oai_token-act-pair · gpt-3.5-turbo

references to legislative acts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Prin

-0.71

hiba

-0.65

cash

-0.64

 Trance

-0.64

via

-0.62

tsky

-0.62

anyl

-0.62

apse

-0.60

sbm

-0.58

itness

-0.58

POSITIVE LOGITS

uary

1.07

 Amendments

1.00

iard

0.86

ional

0.86

uum

0.81

ors

0.81

 enforcement

0.79

icum

0.77

Thumbnail

0.77

ingham

0.74

Activations Density 0.034%

laws or legal acts

references to legislative acts

No Comments

No Known Activations