INDEX

Explanations

phrases related to boundaries or restrictions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ublic

-0.79

lique

-0.73

uni

-0.73

issance

-0.72

stown

-0.69

lÃ©

-0.69

earth

-0.68

asca

-0.68

nian

-0.66

gotten

-0.65

POSITIVE LOGITS

 imposed

0.96

 limits

0.90

 Limits

0.79

lessly

0.76

 limitation

0.75

 limitations

0.74

lessness

0.74

 amount

0.73

 limit

0.73

 allowable

0.72

Activations Density 0.043%

phrases related to boundaries or restrictions

No Comments

No Known Activations