INDEX

Explanations

information about inventions and their inventors

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

inventions and inventors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

twimg

-0.70

 BoxFit

-0.69

 gynhyrchwyd

-0.67

RenderAtEndOf

-0.63

IVEREF

-0.61

 queſta

-0.61

 '\\;'

-0.60

 demurrer

-0.59

piecze

-0.59

 témoig

-0.57

POSITIVE LOGITS

 history

0.48

 invented

0.43

 historical

0.42

 historia

0.41

history

0.40

 historien

0.38

 History

0.38

 storia

0.36

origin

0.35

 originally

0.35

Activations Density 0.121%

information about inventions and their inventors

inventions and inventors

No Comments

No Known Activations

information about inventions and their inventors

inventions and inventors

No Comments

No Known Activations