INDEX

Explanations

instances of the word "First" followed by a number

oai_token-act-pair · gpt-3.5-turbo

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

+++

-0.72

lov

-0.65

sed

-0.65

ITED

-0.62

nz

-0.55

sburgh

-0.54

adian

-0.54

borg

-0.53

erville

-0.53

 horizont

-0.53

POSITIVE LOGITS

Reason

0.76

ly

0.76

 obvious

0.70

 responders

0.67

arily

0.65

hetically

0.64

 Corinthians

0.64

,.

0.63

 thereof

0.62

Activations Density 0.046%

instances of the word "First" followed by a number

No Comments

No Known Activations