INDEX

Explanations

references to the United States

oai_token-act-pair · gpt-3.5-turbo

mentions of the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 exting

-0.71

 newcom

-0.68

 mosqu

-0.68

 summ

-0.68

 eleph

-0.68

 Handling

-0.64

 Discipline

-0.63

ThumbnailImage

-0.63

 moderation

-0.62

 earthqu

-0.61

POSITIVE LOGITS

nexpected

1.02

zbek

1.01

PDATED

0.99

topia

0.96

gly

0.96

mpire

0.94

psc

0.93

sonian

0.93

seless

0.86

prising

0.85

Activations Density 0.036%

references to the United States

mentions of the United States

No Comments

No Known Activations