INDEX

Explanations

mathematical notation and delimiters such as braces and parentheses

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

greek letters and mathematical symbols

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

 Navidad

-0.52

-0.49

nav

-0.45

-0.43

Ste

-0.42

Nav

-0.42

 might

-0.41

-0.39

 will

-0.39

POSITIVE LOGITS

\{\

0.93

=\{

0.89

\{

0.88

 $\{\

0.78

$\{

0.76

}=\{

0.76

$\{

0.76

lbrakk

0.75

featureID

0.75

\{

0.73

Activations Density 0.070%

mathematical notation and delimiters such as braces and parentheses

greek letters and mathematical symbols

No Comments

No Known Activations