INDEX

Explanations

significant contextual markers or tags in structured data

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

context before user

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

Kā

-0.38

Mo

-0.38

Sel

-0.36

Ad

-0.36

 Spin

-0.35

 spin

-0.35

spin

-0.35

ysio

-0.35

mo

-0.34

Zak

-0.34

POSITIVE LOGITS

uxxxx

0.72

 Italijanski

0.71

Personensuche

0.65

 Taktlose

0.63

enderror

0.62

TagMode

0.61

ViewImports

0.60

tagHelperRunner

0.59

tonode

0.59

StandardCharsets

0.58

Activations Density 0.000%

significant contextual markers or tags in structured data

context before user

No Comments

No Known Activations