INDEX

Explanations

number values or parameters associated with different categories or contexts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating variability or comparisons across different categories or demographics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usions

-0.69

redits

-0.65

Buff

-0.65

Effects

-0.64

clips

-0.64

Trivia

-0.62

Adv

-0.62

ensibly

-0.61

phies

-0.61

Imp

-0.61

POSITIVE LOGITS

 region

1.70

 locality

1.69

 province

1.68

 country

1.56

 municipality

1.54

 jurisdiction

1.51

 locale

1.44

 continent

1.42

 city

1.39

 county

1.37

Activations Density 0.504%

number values or parameters associated with different categories or contexts

phrases indicating variability or comparisons across different categories or demographics

No Comments

No Known Activations