INDEX

Explanations

elements indicating stages of progress or commitment in processes or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

neté

-0.59

 intervened

-0.54

 humiliating

-0.52

 severity

-0.52

 poor

-0.51

 usually

-0.50

ijnt

-0.50

unik

-0.50

 parietal

-0.50

どうしても

-0.50

POSITIVE LOGITS

 forward

0.96

future

0.92

 future

0.92

これからの

0.88

 continuare

0.87

これから

0.86

avenir

0.84

 continue

0.83

今後の

0.83

Future

0.82

Activations Density 0.192%

elements indicating stages of progress or commitment in processes or studies

No Comments

No Known Activations