INDEX

Explanations

complex and abstract ideas that are difficult to articulate

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

words that are hard to explain

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

 Roskov

-0.49

 Solon

-0.49

ⓘ

-0.45

 Obrador

-0.45

cipar

-0.43

Fiscal

-0.42

UnusedPrivate

-0.42

apunov

-0.42

 Avid

-0.42

 Fiscal

-0.41

POSITIVE LOGITS

 sentía

0.51

 indefin

0.43

 siente

0.43

 gustaba

0.42

 sentirse

0.42

 sensación

0.41

 <=",

0.41

 vaguely

0.41

 feels

0.40

 sensação

0.40

Activations Density 0.045%

complex and abstract ideas that are difficult to articulate

words that are hard to explain

No Comments

No Known Activations