INDEX

Explanations

structured data representations or metrics

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

user input indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

PCell

-0.43

aarrggbb

-0.42

 térm

-0.42

олові

-0.40

onnaissance

-0.39

Xna

-0.38

ẍ

-0.38

RegressionTest

-0.38

 Италијани

-0.37

nhung

-0.37

POSITIVE LOGITS

tagHelperRunner

0.53

featureID

0.53



0.52

帖最后由

0.51

ViewImports

0.51

Hochspringen

0.50

 незавершена

0.50

Hauptartikel

0.47

rungsseite

0.47

enderror

0.47

Activations Density 0.006%

structured data representations or metrics

user input indicators

No Comments

No Known Activations