INDEX

Explanations

references to historians and historical research methodology

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

historians or history

np_acts-logits-general · gemini-2.0-flash

historian followed by name

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

Identyfik

-0.66

 espri

-0.56

 annonces

-0.55

Handlung

-0.54

makeConstraints

-0.53

 Suède

-0.52

 portefeuille

-0.52

 preghiera

-0.51

Spoljašnje

-0.51

 japonaise

-0.50

POSITIVE LOGITS

 historians

1.96

 historical

1.95

 Historical

1.79

 historian

1.75

historical

1.73

Historical

1.70

 histor

1.70

 Histor

1.50

 history

1.50

 HISTORICAL

1.47

Activations Density 0.658%

references to historians and historical research methodology

historians or history

historian followed by name

No Comments

No Known Activations