INDEX

Explanations

terms related to a specific academic or professional field

oai_token-act-pair · gpt-3.5-turbo

mentions of specific fields or areas of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

éĹĺ

-0.79

nces

-0.72

ILA

-0.71

Es

-0.67

Fas

-0.66

Trans

-0.66

AE

-0.66

Priv

-0.66

Rated

-0.65

ramid

-0.65

POSITIVE LOGITS

 fields

1.03

field

0.97

 field

0.95

fields

0.88

FIELD

0.83

onet

0.81

oller

0.79

ftime

0.73

orer

0.71

cloth

0.71

Activations Density 0.018%

terms related to a specific academic or professional field

mentions of specific fields or areas of study

No Comments

No Known Activations