INDEX

Explanations

mentions related to animated content

oai_token-act-pair · gpt-3.5-turbo

references to animation and animated works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Church

-0.73

chens

-0.72

 Benz

-0.72

Graham

-0.70

 Graham

-0.69

apeake

-0.69

Priv

-0.69

 Patriot

-0.68

RELATED

-0.67

isd

-0.66

POSITIVE LOGITS

 animation

3.74

 animations

2.88

 Animation

2.81

Animation

2.52

 anim

2.03

 animated

1.98

 animate

1.88

anim

1.86

 Animated

1.80

 Anim

1.80

Activations Density 0.013%

mentions related to animated content

references to animation and animated works

No Comments

No Known Activations