INDEX

Explanations

terms related to animation and animated characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

-0.79

ouston

-0.70

hoff

-0.66

ership

-0.66

iability

-0.65

abouts

-0.65

ront

-0.65

ledge

-0.64

agers

-0.63

ighter

-0.63

POSITIVE LOGITS

GIF

0.99

gif

0.90

Preview

0.81

 animation

0.80

 externalToEVAOnly

0.80

oji

0.79

 anim

0.78

agus

0.77

issance

0.76

eer

0.74

Activations Density 0.024%

terms related to animation and animated characters

No Comments

No Known Activations