INDEX

Explanations

specific characters or symbols, indicating a focus on formatting or presentation elements

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

Tokens followed by a number

np_acts-logits-general · gemini-2.0-flash

HTML code and Spanish words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

styleType

-0.81

IsContent

-0.77

 protoimpl

-0.76

ImageContext

-0.75

 Administrativna

-0.74

 الحره

-0.73

tagHelperRunner

-0.72

featureID

-0.71

Хьажоргаш

-0.70

+#+#

-0.70

POSITIVE LOGITS

 Italij

0.47

 duque

0.42

 izquierdo

0.40

 extranjera

0.40

 salvaje

0.39

 restauración

0.38

 literario

0.36

 asesino

0.36

 desierto

0.35

 plateado

0.34

Activations Density 0.083%

specific characters or symbols, indicating a focus on formatting or presentation elements

Tokens followed by a number

HTML code and Spanish words

No Comments

No Known Activations