INDEX

Explanations

symbols or tags typically found in programming or markup languages

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

<start_of_turn>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

PointerException

-0.44

extAlignment

-0.44

исленность

-0.44

principalColumn

-0.41

 везе

-0.41

LayoutStyle

-0.40

ایج

-0.40

 الاطلاع

-0.39

steuer

-0.39

 LEYENDO

-0.39

POSITIVE LOGITS

irited

0.60

 AssemblyCompany

0.56

 Chriftian

0.53

 kasarigan

0.52

Pozdrawiam

0.49

 EconPapers

0.49

sidemargin

0.48

 AssemblyCulture

0.45

oa̍t

0.44

 commerciales

0.43

Activations Density 0.000%

symbols or tags typically found in programming or markup languages

<start_of_turn>user

No Comments

No Known Activations