INDEX

Explanations

tokens and expressions related to mathematical and scientific notation

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

given combination of concepts

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

Życiorys

-0.69

rungsseite

-0.68

Personendaten

-0.61

tanleria

-0.59

 виправивши

-0.58

StructEnd

-0.58

OGND

-0.54

forRoot

-0.52

MigrationBuilder

-0.52

Бележки

-0.51

POSITIVE LOGITS

組み合わせ

0.35

webElementXpaths

0.34

 Transmission

0.32

TiO

0.31

 combination

0.31

tawesome

0.31

λιο

0.31

هما

0.31

sip

0.30

 transmitted

0.30

Activations Density 0.226%

tokens and expressions related to mathematical and scientific notation

given combination of concepts

No Comments

No Known Activations