INDEX

Explanations

mentions of specific languages, especially English, and discussions of language-related topics like proficiency, usage, and education

oai_token-act-pair · gpt-3.5-turbo

references to specific languages and their use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arching

-0.88

urion

-0.88

arcity

-0.84

ocrates

-0.82

ements

-0.81

nuts

-0.78

adium

-0.78

arse

-0.77

arious

-0.77

psy

-0.75

POSITIVE LOGITS

 learners

0.86

 bilingual

0.85

 editions

0.80

 broadcaster

0.80

 interpre

0.80

 dictionary

0.79

 equivalents

0.77

 proficiency

0.76

 translation

0.73

 newspaper

0.72

Activations Density 0.037%

mentions of specific languages, especially English, and discussions of language-related topics like proficiency, usage, and education

references to specific languages and their use

No Comments

No Known Activations