INDEX

Explanations

punctuations and formatting symbols

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

maps and travel

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

AutoField

-0.39

IndentedString

-0.36

hilfe

-0.34

rvore

-0.34

 root

-0.34

[!

-0.34

OneToOne

-0.33

nodoc

-0.33

ustin

-0.33

mentaires

-0.32

POSITIVE LOGITS



0.68

 kasarigan

0.66

الحياه

0.54

VYMaps

0.53

ChildScrollView

0.52

featureID

0.50

帖最后由

0.49

visits

0.49

 autorytatywna

0.49

PYX

0.48

Activations Density 0.000%

punctuations and formatting symbols

maps and travel

No Comments

No Known Activations