INDEX

Explanations

mentions of the word "Reg" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

references to the term "Reg."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lihood

-0.94

¿½

-0.78

 Dangerous

-0.75

hower

-0.73

 Beir

-0.68

ÙĲ

-0.67

CRIPTION

-0.65

 Sense

-0.65

=-=-

-0.64

ĺħ

-0.63

POSITIVE LOGITS

arded

1.17

ardless

1.16

nant

1.14

rett

1.11

ulators

1.10

ulations

1.09

ulatory

1.07

rowth

1.02

arding

1.00

arious

0.98

Activations Density 0.034%

mentions of the word "Reg" followed by a numerical value

references to the term "Reg."

No Comments

No Known Activations