INDEX

Explanations

references to geographical locations and regions

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

geopolitical 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

paksa

-0.42

beelden

-0.41

 înc

-0.40

una

-0.40

実

-0.40

-0.39

SqlClient

-0.39

']))

-0.39

 epä

-0.39

mon

-0.38

POSITIVE LOGITS

ніципалі

0.44

فایل‌لار

0.41

TestingModule

0.41

หวัด

0.40

bootstrapcdn

0.40

Chham

0.40

VIAF

0.39

 '\\;'

0.39

 Numerade

0.38

FieldBuilder

0.38

Activations Density 0.034%

references to geographical locations and regions

geopolitical places

No Comments

No Known Activations

references to geographical locations and regions

geopolitical places

No Comments

No Known Activations