INDEX

Explanations

locations

oai_token-act-pair · gpt-3.5-turbo

references to proximity or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

sheets

-0.71

Topics

-0.65

cook

-0.64

tsky

-0.63

osterone

-0.63

adult

-0.63

 Citizenship

-0.62

 Reneg

-0.62

ication

-0.61

Factor

-0.60

POSITIVE LOGITS

 near

3.21

near

2.78

 Near

1.89

Near

1.83

 nearer

1.68

 close

1.49

 nearby

1.36

 vicinity

1.33

 nearest

1.32

 nearing

1.24

Activations Density 0.027%

locations

references to proximity or location

No Comments

No Known Activations