INDEX

Explanations

mentions of languages and the process of learning languages

oai_token-act-pair · gpt-3.5-turbo

references to linguistic or language-related topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Profit

-0.84

 Rove

-0.84

Pool

-0.81

kefeller

-0.81

 Gamble

-0.80

etheus

-0.80

 Retirement

-0.79

 Roller

-0.79

 Asset

-0.78

 Harley

-0.76

POSITIVE LOGITS

 languages

1.93

 pronunciation

1.89

 bilingual

1.82

 linguistic

1.79

 language

1.78

Language

1.75

ilingual

1.73

 lingu

1.72

 grammar

1.72

 Language

1.70

Activations Density 0.543%

mentions of languages and the process of learning languages

references to linguistic or language-related topics

No Comments

No Known Activations