INDEX

Explanations

URLs related to Wikipedia

oai_token-act-pair · gpt-3.5-turbo

references to Wikipedia links or URLs

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

Reply

-0.75

senal

-0.75

undown

-0.72

hern

-0.70

ONY

-0.68

 mosqu

-0.67

 Samar

-0.67

 Gamble

-0.66

 Brist

-0.64

Ply

-0.63

POSITIVE LOGITS

org

0.93

wiki

0.91

psons

0.79

wik

0.73

ipedia

0.71

ç¥ŀ

0.68

Prev

0.68

Wiki

0.67

ancers

0.66

 Wikimedia

0.65

Activations Density 0.068%

URLs related to Wikipedia

references to Wikipedia links or URLs

No Comments

No Known Activations