INDEX

Explanations

references to pixels or pixel-related details

oai_token-act-pair · gpt-3.5-turbo

terms related to pixel density and pixel art

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jri

-0.84

shore

-0.80

urst

-0.80

ILY

-0.74

etheus

-0.73

IFE

-0.70

kson

-0.70

prise

-0.69

ugu

-0.69

UNE

-0.69

POSITIVE LOGITS

ated

0.82

agraph

0.82

 shader

0.82

Pixel

0.80

ixels

0.78

 Noct

0.75

ters

0.74

 pixels

0.74

 Puzzles

0.73

 Interstellar

0.70

Activations Density 0.020%

references to pixels or pixel-related details

terms related to pixel density and pixel art

No Comments

No Known Activations