INDEX

Explanations

phrases that highlight specific elements or aspects within a sentence

oai_token-act-pair · gpt-3.5-turbo

instances of ambiguity or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

anwhile

-0.63

 staggered

-0.58

itably

-0.56

 scatter

-0.53

 guiActiveUnfocused

-0.53

wagen

-0.53

 scramble

-0.52

ãĥ¼ãĥĨ

-0.52

 spinning

-0.51

 nucleus

-0.51

POSITIVE LOGITS

£

0.85

¹

0.83

catentry

0.76

bryce

0.76

¬

0.74

į

0.72

âĹ¼

0.72

ı

0.71

Â¯

0.71

okia

0.70

Activations Density 0.715%

phrases that highlight specific elements or aspects within a sentence

instances of ambiguity or uncertainty

No Comments

No Known Activations