INDEX

Explanations

academic or scientific terminology and concepts

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

describing suggested mechanisms or attributions

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

 Biôgrafia

-0.59

posedge

-0.58

 protoimpl

-0.57

GOTREF

-0.55

queryInterface

-0.54

 Administrativna

-0.51

 demografica

-0.50

SpringBootTest

-0.50

oredCriteria

-0.49

 ProtoMessage

-0.48

POSITIVE LOGITS

 Rég

0.40

But

0.35

发表于

0.35

openSession

0.33

 primes

0.31

yet

0.31

 Americans

0.31

but

0.31

BindingSource

0.30

CrossRef

0.29

Activations Density 0.280%

academic or scientific terminology and concepts

describing suggested mechanisms or attributions

No Comments

No Known Activations