INDEX

Explanations

words related to standards or criteria

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Stars

-0.77

cig

-0.76

lez

-0.75

acan

-0.68

 Psychiat

-0.67

sen

-0.66

resent

-0.64

SEE

-0.60

usters

-0.60

INESS

-0.59

POSITIVE LOGITS

 deviation

1.34

 deviations

1.26

 bearer

1.09

ised

1.02

ization

0.96

arily

0.92

isation

0.92

izes

0.88

 standard

0.87

é¾įå¥ĳå£«

0.84

Activations Density 0.014%

words related to standards or criteria

No Comments

No Known Activations