INDEX

Explanations

the beginning of text segments marked by special tokens

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

multilingual technical or specific context

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 deres

-0.41

väg

-0.38

 here

-0.38

 progresso

-0.38

 sempurna

-0.38

 नीचे

-0.37

 अलावा

-0.37

 garganta

-0.36

รุ่น

-0.35

 baris

-0.35

POSITIVE LOGITS

хьтан

1.16

ंदीखरीदारी

1.15

دانشنامهٔ

1.11

 Савезне

1.08

contentLoaded

1.05

 AssemblyCulture

1.03

kháu

1.02

 cherchés

1.02

 kasarigan

1.01

uxxxx

1.01

Activations Density 0.021%

the beginning of text segments marked by special tokens

multilingual technical or specific context

No Comments

No Known Activations