INDEX

Explanations

version numbers or identifiers associated with software

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

version numbers after v

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

CELLANEOUS

-0.43

imwrite

-0.36

eseorang

-0.36

PointerException

-0.35

 Italijani

-0.34

MathML

-0.34

 noDo

-0.34

hilangan

-0.34

feitura

-0.33

yaszt

-0.33

POSITIVE LOGITS

 version

0.91

 Version

0.84

 versions

0.72

Version

0.70

version

0.69

 VERSION

0.68

getVersion

0.65

 versione

0.64

 Versions

0.64

Activations Density 0.044%

version numbers or identifiers associated with software

version numbers after v

No Comments

No Known Activations