INDEX

Explanations

phrases indicating causality or transition between ideas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orld

-0.72

 sought

-0.68

gad

-0.62

 dwell

-0.60

ortium

-0.59

perty

-0.58

farious

-0.58

ilee

-0.58

ially

-0.58

iste

-0.58

POSITIVE LOGITS

 Mahjong

0.76

hift

0.74

ï¸

0.72

 THREE

0.67

ebin

0.67

ems

0.67

Plus

0.67

ECA

0.66

 GOODMAN

0.64

Tau

0.64

Activations Density 0.194%

phrases indicating causality or transition between ideas

No Comments

No Known Activations