INDEX

Explanations

questions or queries

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

 celebr

-0.62

 proud

-0.62

Khe

-0.59

 analges

-0.58

 inclusion

-0.58

 migration

-0.58

 contag

-0.58

 invisible

-0.57

 contagious

-0.57

 belonging

-0.57

POSITIVE LOGITS

Answer

1.38

Well

1.08

ÂłÂłÂłÂł

0.99

Absolutely

0.97

Yes

0.95

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.91

Honestly

0.91

Correct

0.88

ÂłÂłÂłÂłÂłÂłÂłÂł

0.88

Probably

0.87

Activations Density 0.136%

questions or queries

No Comments

No Known Activations