INDEX

Explanations

numeric data values within structured datasets

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

code blocks and numbers

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

RenderAtEndOf

-0.50

pushFollow

-0.48

verwijspagina

-0.47

GraphicsUnit

-0.46

IBarButtonItem

-0.45

뀔

-0.45

лтамалар

-0.45

thenReturn

-0.44

:✨

-0.44

紹介します

-0.44

POSITIVE LOGITS

 تانيه

0.47

TintMode

0.44

脚注の使い方

0.42

 uLocal

0.40

 enfans

0.40

adaptiveStyles

0.39

Frances

0.34

 planches

0.33

 pouvoit

0.33

richTextPanel

0.32

Activations Density 0.031%

numeric data values within structured datasets

code blocks and numbers

No Comments

No Known Activations