INDEX

Explanations

mentions of the term "screen" in various contexts related to film and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ortium

-0.84

onomic

-0.77

coh

-0.76

yip

-0.70

toc

-0.66

Sym

-0.66

doms

-0.65

imal

-0.61

 Statistical

-0.61

laus

-0.61

POSITIVE LOGITS

plays

1.42

writers

1.28

writer

1.24

writing

1.03

ographer

0.90

 adaptation

0.85

acters

0.83

wright

0.80

 depiction

0.80

 depictions

0.79

Activations Density 0.009%

mentions of the term "screen" in various contexts related to film and media

No Comments

No Known Activations