INDEX

Explanations

a pattern related to numerical data and statistics

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and rarity classifications

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

ĸļ

-0.92

 acknow

-0.73

 parad

-0.72

 sche

-0.68

 plank

-0.68

 memo

-0.67

 respons

-0.66

 headlights

-0.66

 rend

-0.65

 both

-0.65

POSITIVE LOGITS

Ranked

1.46

Average

1.29

Percent

1.24

Total

1.23

Avg

1.16

Completed

1.14

Overall

1.13

Hig

1.11

Number

1.05

Lost

1.04

Activations Density 0.078%

a pattern related to numerical data and statistics

references to statistical data and rarity classifications

No Comments

No Known Activations