INDEX

Explanations

instances of the word "appear" and its variations

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

dp

-0.82

EStreamFrame

-0.76

shaw

-0.76

aign

-0.70

cise

-0.68

hov

-0.66

ced

-0.63

brid

-0.62

currency

-0.61

Ã§a

-0.61

POSITIVE LOGITS

 onstage

0.78

 poised

0.73

 prominently

0.70

ãĤ¤ãĥĪ

0.66

 victorious

0.63

Pause

0.63

earance

0.61

 briefly

0.60

inet

0.60

vind

0.59

Activations Density 0.024%

instances of the word "appear" and its variations

No Comments

No Known Activations