INDEX

Explanations

phrases related to names or titles

oai_token-act-pair · gpt-3.5-turbo

proper nouns associated with specific individuals and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

poke

-0.69

MPH

-0.65

 ORDER

-0.64

perty

-0.61

nyder

-0.59

vic

-0.57

 Adin

-0.57

 subtract

-0.56

PW

-0.56

 lifespan

-0.55

POSITIVE LOGITS

rette

1.02

ĸļ

0.77

Ã±a

0.74

®

0.73

agne

0.72

anne

0.72

Ã©e

0.70

oute

0.70

uce

0.69

onen

0.68

Activations Density 0.102%

phrases related to names or titles

proper nouns associated with specific individuals and places

No Comments

No Known Activations