INDEX

Explanations

words related to tiling, particularly focusing on the word "tiles" specifically

oai_token-act-pair · gpt-3.5-turbo

references to tiles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ulner

-0.86

ivia

-0.78

ntil

-0.77

anchester

-0.76

irl

-0.72

ijah

-0.71

etheus

-0.71

ournal

-0.68

avez

-0.68

 largeDownload

-0.68

POSITIVE LOGITS

 tiles

1.22

 tile

1.07

 Tile

1.02

 grids

0.85

 wallpaper

0.85

 Walls

0.82

 mosaic

0.78

 decoration

0.78

 sheets

0.77

glass

0.75

Activations Density 0.007%

words related to tiling, particularly focusing on the word "tiles" specifically

references to tiles

No Comments

No Known Activations