INDEX

Explanations

proper nouns related to titles or names

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns and terms related to geographical and media references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

maxwell

-0.88

ĸļ

-0.85

sylvania

-0.85

orage

-0.82

ored

-0.81

ory

-0.81

oring

-0.80

orer

-0.79

orius

-0.78

ower

-0.76

POSITIVE LOGITS

lly

0.82

 Flavoring

0.76

cloth

0.73

Nou

0.72

Ã§a

0.71

Ã±o

0.70

naissance

0.70

 Negro

0.70

vier

0.65

Pwr

0.65

Activations Density 0.028%

proper nouns related to titles or names

specific proper nouns and terms related to geographical and media references

No Comments

No Known Activations