INDEX

Explanations

references to scientific and medical terminology related to biological processes and substances

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

everywhere

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

OGND

-0.71

(!__

-0.69

 AssemblyCompany

-0.67

 ویکی‌پدی

-0.67

ThroughAttribute

-0.64

 EconPapers

-0.61

 незавершена

-0.57

دانشنامهٔ

-0.52

 intptr

-0.49

MockMvc

-0.48

POSITIVE LOGITS

 везде

0.47

 everywhere

0.44

 Everywhere

0.43

Everywhere

0.40

 partout

0.38

 ovunque

0.38

everywhere

0.36

 überall

0.35

 سواء

0.35

 baik

0.34

Activations Density 0.122%

references to scientific and medical terminology related to biological processes and substances

everywhere

No Comments

No Known Activations