INDEX

Explanations

punctuations and formatting changes in the text

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

nature and liberty

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

 utafitiHapana

-0.53

 Majefty

-0.52

IntoConstraints

-0.52

__':

-0.52

 MainAxisSize

-0.51

 يتيمه

-0.50

 BorderSide

-0.50

 виправивши

-0.50

}{*}{

-0.49

 éché

-0.48

POSITIVE LOGITS

are

0.42

település

0.40

 suffice

0.39

Slf

0.36

ได้

0.35

Среди

0.35

Evet

0.35

 suffices

0.34

 have

0.34

Activations Density 0.093%

punctuations and formatting changes in the text

nature and liberty

No Comments

No Known Activations

punctuations and formatting changes in the text

nature and liberty

No Comments

No Known Activations