INDEX

Explanations

words related to animation techniques or processes

oai_token-act-pair · gpt-3.5-turbo

terms related to animation and animated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

holder

-0.82

hoff

-0.71

 Prescott

-0.67

 Norton

-0.67

inness

-0.67

ront

-0.64

patrick

-0.64

marks

-0.63

ouston

-0.63

ructure

-0.62

POSITIVE LOGITS

GIF

1.04

gif

0.93

oji

0.78

agus

0.78

Preview

0.77

 studios

0.74

 animation

0.73

 Studios

0.72

issance

0.72

 anim

0.71

Activations Density 0.041%

words related to animation techniques or processes

terms related to animation and animated content

No Comments

No Known Activations