INDEX

Explanations

mentions of the word "animation."

oai_token-act-pair · gpt-3.5-turbo

references to animation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ennett

-0.75

VEN

-0.75

ESS

-0.73

utherford

-0.71

uckle

-0.71

umbing

-0.71

asper

-0.70

-0.69

ighter

-0.68

agers

-0.67

POSITIVE LOGITS

 animation

1.29

 animations

1.05

 Animation

0.94

GIF

0.93

 anim

0.89

cember

0.88

Animation

0.83

 Anim

0.80

gif

0.79

oji

0.72

Activations Density 0.008%

mentions of the word "animation."

references to animation

No Comments

No Known Activations