INDEX

Explanations

names or references related to the city of San Francisco

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Fr" and variations suggesting geographical or cultural references associated with France

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Jinn

-0.85

 Izan

-0.66

 arteries

-0.64

 Wonders

-0.62

 Contrast

-0.61

 Siren

-0.61

 Archdemon

-0.60

fml

-0.59

orney

-0.58

 guiActiveUnfocused

-0.57

POSITIVE LOGITS

isco

1.00

ruary

0.88

atism

0.79

furt

0.77

ulent

0.71

issance

0.70

rance

0.68

eners

0.65

amus

0.64

aternity

0.64

Activations Density 0.072%

names or references related to the city of San Francisco

instances of the word "Fr" and variations suggesting geographical or cultural references associated with France

No Comments

No Known Activations