INDEX

Explanations

Hebrew characters or words

oai_token-act-pair · gpt-3.5-turbo

non-English characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ovie

-0.93

gdala

-0.85

ooth

-0.81

holes

-0.77

 newsp

-0.75

ellen

-0.73

essa

-0.71

sonian

-0.70

 Flavoring

-0.69

leground

-0.68

POSITIVE LOGITS

à¤

1.38

Ĺ

1.25

×

1.13

¤

1.11

×ķ

1.10

×Ļ

1.07

 à¤

1.04

ĵ

1.04

ķ

1.04

¢

1.02

Activations Density 0.001%

Hebrew characters or words

non-English characters or symbols

No Comments

No Known Activations