INDEX

Explanations

additional information or references within a text

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate additional information or further reading resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Ïī

-0.91

livion

-0.81

adr

-0.77

assic

-0.75

oise

-0.73

ceans

-0.73

riz

-0.72

orney

-0.70

Downloadha

-0.70

rez

-0.68

POSITIVE LOGITS

 Examples

1.18

 Locations

1.12

 Features

1.12

 Thoughts

1.11

 Results

1.10

 Stories

1.06

 Contents

1.04

 Comments

1.04

 Items

1.04

 Categories

1.02

Activations Density 0.155%

additional information or references within a text

phrases that indicate additional information or further reading resources

No Comments

No Known Activations