INDEX

Explanations

phrases associated with legal terminology and related contexts

oai_token-act-pair · gpt-3.5-turbo

the character "ÂŃ" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ÃŃa

-0.66

NX

-0.65

otine

-0.65

idad

-0.65

 Brach

-0.64

Yen

-0.64

 Robot

-0.64

 plaque

-0.64

ulhu

-0.63

yz

-0.63

POSITIVE LOGITS

Â£

0.96

selves

0.91

contin

0.91

recent

0.89

reve

0.89

âĢ¢âĢ¢âĢ¢âĢ¢

0.89

tem

0.89

cour

0.88

rec

0.88

coll

0.87

Activations Density 0.007%

phrases associated with legal terminology and related contexts

the character "ÂŃ" in various contexts

No Comments

No Known Activations