INDEX

Explanations

technical terms, scientific measurements, and references to equipment or methodologies in research

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

court cases and legal citations

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

Personendaten

-0.75

 bezeichneter

-0.74

 Мексичка

-0.69

GOTREF

-0.67

 Wikiseite

-0.60

 Roskov

-0.60

Manbalar

-0.59

Geografía

-0.57

antaranya

-0.57

SharedCtor

-0.56

POSITIVE LOGITS

0.63

0.48

gua

0.47

dia

0.47

iol

0.46

mias

0.46

wadi

0.46

Dem

0.46

duc

0.45

iform

0.45

Activations Density 1.777%

technical terms, scientific measurements, and references to equipment or methodologies in research

court cases and legal citations

No Comments

No Known Activations