INDEX

Explanations

specific code structure and variable definitions

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

After punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

reg or Rég variations

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

 Aniston

-0.54

stø

-0.49

führt

-0.48

ั่ว

-0.44

 Ashford

-0.43

zuführen

-0.43

teine

-0.42

 Noël

-0.41

 simplifié

-0.41

 Neuer

-0.41

POSITIVE LOGITS

reg

1.11

Reg

0.99

REG

0.97

 Riggs

0.96

ag

0.96

Reg

0.95

reg

0.94

Rég

0.93

REG

0.91

Ag

0.89

Activations Density 0.483%

specific code structure and variable definitions

After punctuation or symbols

reg or Rég variations

No Comments

No Known Activations