INDEX

Explanations

phrases indicating collaboration or association between entities

oai_token-act-pair · gpt-3.5-turbo

words related to companionship or group actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Origin

-0.55

 Radius

-0.52

 Minotaur

-0.51

 Conquer

-0.50

 hump

-0.50

 Walls

-0.50

 RELE

-0.48

 Reach

-0.48

 unpre

-0.47

 downed

-0.47

POSITIVE LOGITS

by

1.33

by

1.01

By

0.87

retty

0.84

BY

0.82

uthor

0.81

By

0.77

igious

0.76

rius

0.76

Ń·

0.72

Activations Density 0.178%

phrases indicating collaboration or association between entities

words related to companionship or group actions

No Comments

No Known Activations