INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

references to items or elements related to specific works or contributions

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

å¥³

-0.82

sth

-0.77

EST

-0.76

ivation

-0.71

etz

-0.70

meal

-0.66

ername

-0.66

henko

-0.65

hest

-0.65

POSITIVE LOGITS

 various

1.41

 varying

1.27

 different

1.16

 other

1.12

 assorted

1.11

 disparate

1.01

 numerous

0.97

 differing

0.96

 Various

0.95

 others

0.94

Activations Density 0.551%

proper nouns and names

references to items or elements related to specific works or contributions

No Comments

No Known Activations