INDEX

Explanations

specific tokens and tags related to metadata or formatting within a document

oai_token-act-pair · gpt-3.5-turbo

the presence of the letter "O" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Yel

-0.80

CRC

-0.67

 butterflies

-0.65

 Shepard

-0.64

 totality

-0.63

PLA

-0.62

 indexes

-0.61

 Yuri

-0.60

 oranges

-0.59

 prism

-0.59

POSITIVE LOGITS

lymp

1.41

culus

1.37

mega

1.35

ceans

1.32

rient

1.29

vernight

1.27

liv

1.26

scill

1.23

tto

1.19

scar

1.17

Activations Density 0.022%

specific tokens and tags related to metadata or formatting within a document

the presence of the letter "O" in various contexts

No Comments

No Known Activations