INDEX

Explanations

detailed or thorough analysis and explanations

oai_token-act-pair · gpt-3.5-turbo

references to analysis or examination of topics in depth

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prov

-0.72

 substitute

-0.65

 substitutes

-0.64

 Swan

-0.63

dod

-0.63

 volunteers

-0.62

 cheer

-0.62

Mr

-0.62

 domestic

-0.62

 male

-0.61

POSITIVE LOGITS

depth

3.97

Depth

2.47

 depth

2.04

 Depth

1.97

DEP

1.44

length

1.36

detail

1.18

 depths

1.18

deep

1.13

radius

1.13

Activations Density 0.015%

detailed or thorough analysis and explanations

references to analysis or examination of topics in depth

No Comments

No Known Activations