INDEX

Explanations

dates or years

oai_token-act-pair · gpt-3.5-turbo

references to years and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

raltar

-0.83

awed

-0.77

rophe

-0.76

ledged

-0.75

ysical

-0.75

ramid

-0.75

otle

-0.74

rotein

-0.72

 behavi

-0.72

ãĤ©

-0.69

POSITIVE LOGITS

nd

1.51

naire

0.92

0.87

0.82

ND

0.82

ipop

0.81

0.79

0.78

Activations Density 0.057%

dates or years

references to years and numerical data

No Comments

No Known Activations