INDEX

Explanations

words related to blame or responsibility being assigned to someone or something

oai_token-act-pair · gpt-3.5-turbo

references to blame or responsibility in various contexts

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

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

atos

-0.89

hedral

-0.73

ISTER

-0.73

het

-0.72

xon

-0.71

thia

-0.71

CHO

-0.71

ague

-0.70

¥µ

-0.70

cheat

-0.68

POSITIVE LOGITS

lessly

1.16

ously

0.91

å£«

0.80

 Karma

0.78

lessness

0.76

 forgiven

0.76

less

0.74

 fault

0.73

à©

0.73

 faults

0.71

Activations Density 0.077%

words related to blame or responsibility being assigned to someone or something

references to blame or responsibility in various contexts

No Comments

No Known Activations