INDEX

Explanations

shapes or descriptions related to physical forms

oai_token-act-pair · gpt-3.5-turbo

references to different shapes and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

amily

-0.73

artment

-0.72

onte

-0.70

uthor

-0.66

unts

-0.66

Mub

-0.65

uable

-0.64

ILLE

-0.64

iance

-0.63

GS

-0.63

POSITIVE LOGITS

shape

1.18

 shape

1.12

 shapes

1.01

 shif

0.95

 Shape

0.92

Shape

0.85

 shaped

0.84

cut

0.80

 formation

0.79

 morp

0.78

Activations Density 0.019%

shapes or descriptions related to physical forms

references to different shapes and their descriptions

No Comments

No Known Activations