INDEX

Explanations

references to clarification or explanations of terms

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

disambiguation

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

 little

-0.38

 regional

-0.35

-0.34

relse

-0.34

 living

-0.34

 подо

-0.33

Regional

-0.33

 Regional

-0.33

InSection

-0.32

POSITIVE LOGITS

Begriffsklä

5.00

verwijspagina

2.83

曖昧さ回避

2.08

 disambiguazione

2.03

homonymie

1.61

 ujednoznacz

1.29

Personendaten

1.11

disambiguation

1.02

rungsseite

1.00

niająca

0.85

Activations Density 0.000%

references to clarification or explanations of terms

disambiguation

No Comments

No Known Activations