INDEX

Explanations

titles of movies, TV shows, and video games

oai_token-act-pair · gpt-3.5-turbo

phrases or references related to "of" 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 @ 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

 Cosponsors

-0.82

gallery

-0.82

 contrace

-0.78

wcs

-0.78

ucci

-0.72

 ensu

-0.72

eson

-0.72

mson

-0.71

jee

-0.70

 nodd

-0.69

POSITIVE LOGITS

 Darkness

1.00

 Legends

0.95

 Awakening

0.95

 Titans

0.92

 Mysteries

0.91

 Champions

0.87

 Terror

0.86

 Cortex

0.85

 Chaos

0.85

 Thieves

0.83

Activations Density 0.067%

titles of movies, TV shows, and video games

phrases or references related to "of" in various contexts

No Comments

No Known Activations