INDEX

Explanations

terms related to mathematical expressions and operations

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

average over directions

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

ltä

-0.42

 enfans

-0.37

 étoient

-0.36

 mérit

-0.36

 chrétiens

-0.36

 avoient

-0.36

 malheur

-0.36

 lizenzfreies

-0.36

 laaj

-0.35

 réal

-0.35

POSITIVE LOGITS

InputBorder

0.50

ChildScrollView

0.48

 insuffisamment

0.47

sidemargin

0.47

Чыгана

0.47

oneofs

0.47

popd

0.45

CppMethod

0.45

󠁴

0.45

detectChanges

0.45

Activations Density 0.059%

terms related to mathematical expressions and operations

average over directions

No Comments

No Known Activations