INDEX

Explanations

references to assumed identities, particularly in the context of underground activities

oai_token-act-pair · gpt-3.5-turbo

themes related to identity and transformation, particularly in a social or cultural context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eur

-0.58

olean

-0.58

pires

-0.58

itiz

-0.55

atform

-0.53

 divides

-0.52

 reader

-0.51

tains

-0.50

 Coverage

-0.50

cest

-0.50

POSITIVE LOGITS

 themselves

1.28

selves

1.22

 selves

1.05

 respectively

0.98

were

0.92

 were

0.91

 weren

0.87

 numbered

0.83

 individually

0.83

their

0.81

Activations Density 1.580%

references to assumed identities, particularly in the context of underground activities

themes related to identity and transformation, particularly in a social or cultural context

No Comments

No Known Activations