INDEX

Explanations

terms related to classifications, descriptions, and assessments

oai_token-act-pair · gpt-3.5-turbo

terms and phrases relevant to descriptions, proposals, and laws within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ovember

-0.62

cms

-0.60

rontal

-0.59

});

-0.57

 awaits

-0.56

otted

-0.55

 ensued

-0.53

aylor

-0.53

lat

-0.53

eties

-0.53

POSITIVE LOGITS

 differently

1.28

as

1.20

 favorably

1.13

 negatively

0.83

as

0.81

 skept

0.81

 positively

0.81

 symp

0.71

 solely

0.70

 unfairly

0.70

Activations Density 0.258%

terms related to classifications, descriptions, and assessments

terms and phrases relevant to descriptions, proposals, and laws within various contexts

No Comments

No Known Activations