INDEX

Explanations

dates and months

oai_token-act-pair · gpt-3.5-turbo

dates and months mentioned in the text

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

Reviewer

-0.74

illin

-0.68

amines

-0.63

 quot

-0.62

 bastard

-0.60

 VIDEOS

-0.60

ourge

-0.57

 itch

-0.56

bom

-0.56

lac

-0.56

POSITIVE LOGITS

0.91

0.88

flower

0.87

ruary

0.87

 afternoon

0.86

 mornings

0.85

0.84

fair

0.82

Activations Density 0.081%

dates and months

dates and months mentioned in the text

No Comments

No Known Activations