INDEX

Explanations

terms related to residential and community environments

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

residential areas and quiet places

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

Carriera

-0.53

lgari

-0.48

 Keuangan

-0.46

 EconPapers

-0.44

 ejército

-0.44

MessageOf

-0.43

 descuentos

-0.43

folios

-0.43

 puentes

-0.42

 prisonniers

-0.42

POSITIVE LOGITS

 "..\..\

0.55

 "..\..\..\

0.52

 quiet

0.48

 Quiet

0.46

 privacy

0.46

 Rest

0.44

Quiet

0.42

ftagPool

0.42

 private

0.42

 road

0.41

Activations Density 0.001%

terms related to residential and community environments

residential areas and quiet places

No Comments

No Known Activations