INDEX

Explanations

references to the music genre "reggae."

oai_token-act-pair · gpt-3.5-turbo

references to regulatory or governmental topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Hole

-0.78

 Heck

-0.78

 Trap

-0.77

lihood

-0.74

Fey

-0.74

 Traps

-0.73

WARE

-0.73

hower

-0.73

 Realms

-0.72

 Maze

-0.70

POSITIVE LOGITS

roup

1.22

ressive

1.15

rowth

1.06

gae

1.02

inal

1.01

cit

0.99

rant

0.97

roups

0.97

itted

0.96

aining

0.96

Activations Density 0.012%

references to the music genre "reggae."

references to regulatory or governmental topics

No Comments

No Known Activations