INDEX

Explanations

specific characters or symbols commonly associated with names in various languages

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

foreign and proper names

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

RegressionTest

-0.61

expandindo

-0.60

 חיצוניים

-0.60

addGap

-0.52

تقاوى

-0.51

 kautta

-0.49

rungsseite

-0.48

SharedDtor

-0.47

weightedMode

-0.47

BibitemShut

-0.46

POSITIVE LOGITS

 "..\..\..\

0.42

----</

0.41

 Democratic

0.39

thâu

0.39

 ostavi

0.37

(!__

0.36

 Administrativna

0.36

Democratic

0.36

########.

0.35

++]=

0.34

Activations Density 0.005%

specific characters or symbols commonly associated with names in various languages

foreign and proper names

No Comments

No Known Activations