INDEX

Explanations

references to academic publications and citations

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

publishers

np_acts-logits-general · gemini-2.0-flash

academic publishers and imprints

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.64

LookAnd

-0.60

InjectAttribute

-0.53

loped

-0.49

 trouvait

-0.49

cheduler

-0.49

TagMode

-0.48

 processing

-0.48

 ArrayAdapter

-0.48

jaz

-0.48

POSITIVE LOGITS

sons

0.64

UseVisualStyle

0.59

μφωνα

0.53

0.50

Scientific

0.48

 Scientific

0.47

 Pearson

0.47

 SCIENTIFIC

0.47

 ویکی‌پدیای

0.47

 Prentice

0.46

Activations Density 0.321%

references to academic publications and citations

publishers

academic publishers and imprints

No Comments

No Known Activations