INDEX

Explanations

technology-related terms and names associated with digital platforms

oai_token-act-pair · gpt-3.5-turbo

references to Google services and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.71

 trauma

-0.68

usp

-0.65

Narr

-0.65

 Appalachian

-0.64

rar

-0.63

displayText

-0.62

istered

-0.61

cir

-0.60

ĪĴ

-0.60

POSITIVE LOGITS

opol

0.75

Plex

0.73

vine

0.73

ipedia

0.73

Xbox

0.70

merce

0.70

Shop

0.68

flix

0.66

 Glow

0.64

enhagen

0.64

Activations Density 0.210%

technology-related terms and names associated with digital platforms

references to Google services and products

No Comments

No Known Activations