INDEX

Explanations

mentions of, or related to, licenses

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lans

-0.90

 IMAGES

-0.76

selves

-0.73

te

-0.72

ilight

-0.67

TING

-0.67

sonian

-0.65

telling

-0.64

ahi

-0.64

agic

-0.64

POSITIVE LOGITS

 licenses

0.98

 revocation

0.96

 plate

0.93

license

0.92

enses

0.90

License

0.88

 plates

0.88

 renewal

0.85

ensing

0.85

 license

0.85

Activations Density 0.040%

mentions of, or related to, licenses

No Comments

No Known Activations