INDEX

Explanations

dates written in a specific format

oai_token-act-pair · gpt-3.5-turbo

numerical dates and significant time markers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

------------------------

-0.95

 Huss

-0.83

 horm

-0.81

 Greenberg

-0.79

Magn

-0.78

 Hasan

-0.77

 Herm

-0.76

Hag

-0.76

hap

-0.75

 Sherman

-0.73

POSITIVE LOGITS

1.42

1.31

1.11

0.95

0.89

0.88

aton

0.82

0.80

å¤§

0.78

Activations Density 0.279%

dates written in a specific format

numerical dates and significant time markers

No Comments

No Known Activations