INDEX

Explanations

metadata related to editing

oai_token-act-pair · gpt-3.5-turbo

brackets or references to sections within a list or documentation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 comprom

-0.80

 eleph

-0.78

everal

-0.76

oun

-0.72

 conduc

-0.71

 misunder

-0.71

 occas

-0.69

 thous

-0.68

'';

-0.65

 gobl

-0.65

POSITIVE LOGITS

 edit

1.86

 Edit

1.56

?]

1.27

edit

1.22

][

1.14

1.08

Â¶

1.08

 citation

1.01

Edit

0.96

][

0.92

Activations Density 0.009%

metadata related to editing

brackets or references to sections within a list or documentation

No Comments

No Known Activations