INDEX

Explanations

phrases that indicate recognition or reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AndEndTag

-0.56

CompleteListener

-0.52

onges

-0.51

زيون

-0.51

rawDesc

-0.51

 Topography

-0.51

nivå

-0.50

cstdio

-0.49

 gevolg

-0.49

 prochains

-0.48

POSITIVE LOGITS

 worldwide

0.73

 amongst

0.68

maßen

0.68

among

0.66

 among

0.64

 internationally

0.61

worldwide

0.58

 collo

0.57

isable

0.57

 mundial

0.57

Activations Density 0.106%

phrases that indicate recognition or reputation

No Comments

No Known Activations