INDEX

Explanations

code-related syntax elements and attributes

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

Text within brackets/parentheses with data labels

np_acts-logits-general · gemini-2.0-flash

XML attributes and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 MainAxisSize

-0.92

 Chwiliwch

-0.89

 المعيارى

-0.77

GTCX

-0.76

__":

-0.73

 للمعارف

-0.73

 Houſe

-0.72

GEBURTSDATUM

-0.72

AnchorStyles

-0.71

MLLoader

-0.71

POSITIVE LOGITS

有

0.38

 zvuky

0.38

Sal

0.35

data

0.35

SAL

0.34

info

0.33

room

0.32

™

0.32

要

0.32

Activations Density 0.820%

code-related syntax elements and attributes

Text within brackets/parentheses with data labels

XML attributes and values

No Comments

No Known Activations