INDEX

Explanations

terms that denote scientific or mathematical notation and variable representations

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

subscripted abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 driven

-0.34

 leña

-0.29

 traditionally

-0.29

 cuidadosamente

-0.27

 précision

-0.26

 Ansicht

-0.25

 suele

-0.24

 vícti

-0.24

 Gestión

-0.24

别

-0.24

POSITIVE LOGITS

IConfiguration

1.38

 IConfiguration

1.29

SpringBootTest

0.96

出版年

0.81

tagHelperRunner

0.75

IndentedString

0.75

 NSCoder

0.74

Viitteet

0.73

хьтан

0.73

RTEE

0.72

Activations Density 0.001%

terms that denote scientific or mathematical notation and variable representations

subscripted abbreviations

No Comments

No Known Activations