INDEX

Explanations

structural elements and formatting markers in text

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

structured text formatting

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

 informée

-0.88

Personendaten

-0.77

 HasFactory

-0.73

 صوتيه

-0.73

 AssemblyCulture

-0.70

 للاسماء

-0.69

richTextPanel

-0.66

IsContent

-0.66

 surla

-0.65

AxisAlignment

-0.63

POSITIVE LOGITS

 ſte

0.41

 sulf

0.36

 faſt

0.35

sulf

0.35

江

0.33

 excel

0.33

<0xE9>

0.33

 talking

0.32

Sulf

0.32

 inside

0.31

Activations Density 0.001%

structural elements and formatting markers in text

structured text formatting

No Comments

No Known Activations