INDEX

Explanations

phrases related to layout customization

oai_token-act-pair · gpt-3.5-turbo

references to various types of layouts

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

icer

-1.04

hood

-0.89

jamin

-0.82

 Lauder

-0.81

nard

-0.75

elope

-0.73

tein

-0.72

thood

-0.71

ute

-0.71

unts

-0.70

POSITIVE LOGITS

 layouts

1.32

 layout

1.25

 Layout

1.14

 diagrams

0.94

 diagram

0.90

layout

0.87

Layout

0.80

 spacing

0.80

 mismatch

0.79

 schematic

0.78

Activations Density 0.027%

phrases related to layout customization

references to various types of layouts

No Comments

No Known Activations