INDEX

Explanations

sentences related to criticism or disapproval

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 disadvantaged

-0.55

 subcontract

-0.54

 Reincarnated

-0.54

oppable

-0.53

 ..............

-0.52

 Tycoon

-0.52

 discriminated

-0.52

 customs

-0.51

 Fighting

-0.50

 Transition

-0.50

POSITIVE LOGITS

 reader

0.84

 journalistic

0.80

ascript

0.76

 rhetorical

0.74

reader

0.74

canon

0.72

 cynicism

0.72

entious

0.69

 editorial

0.68

 readers

0.68

Activations Density 1.161%

sentences related to criticism or disapproval

No Comments

No Known Activations