INDEX

Explanations

elements describing shared human experiences or social conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

EndInit

-0.58

stoj

-0.51

ArgumentParser

-0.51

 विश्वसनीयता

-0.49

.}\

-0.47

=""></

-0.46

 permitió

-0.46

 нейтра

-0.45

ectoria

-0.44

findFirst

-0.43

POSITIVE LOGITS

 obsession

1.02

 nonstop

0.97

 devote

0.97

 obses

0.95

 obsessed

0.93

 dedicate

0.90

 devoting

0.89

 incess

0.88

 constantly

0.86

obses

0.86

Activations Density 0.280%

elements describing shared human experiences or social conditions

No Comments

No Known Activations