INDEX

Explanations

phrases indicating permission or preference

oai_token-act-pair · gpt-3.5-turbo

expressions related to personal choice and preference

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Peach

-0.63

åĭ

-0.61

 Samp

-0.61

 Vikings

-0.57

 Creed

-0.56

 frog

-0.55

ipers

-0.55

 Norman

-0.55

 Catal

-0.55

QL

-0.54

POSITIVE LOGITS

.''.

0.72

.--

0.70

.","

0.69

itably

0.68

 ende

0.61

phasis

0.60

.—

0.60

tenance

0.60

ably

0.60

igne

0.59

Activations Density 0.400%

phrases indicating permission or preference

expressions related to personal choice and preference

No Comments

No Known Activations