INDEX

Explanations

mathematical and matrix-related symbols and notations

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

latex matrix environments

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

featureID

-0.78

:✨

-0.66

 transfieras

-0.65

KommentareTeilen

-0.64

 EconPapers

-0.63

verwijspagina

-0.63

StoryboardSegue

-0.60

TextWatcher

-0.60

<unused3>

-0.59

<unused52>

-0.59

POSITIVE LOGITS

siębior

0.29

richTextPanel

0.25

္

0.24

哪

0.24

JAMES

0.24

第三

0.24

 jubile

0.24

squ

0.24

 como

0.23

چ

0.23

Activations Density 0.765%

mathematical and matrix-related symbols and notations

latex matrix environments

No Comments

No Known Activations