INDEX

Explanations

punctuation usage, particularly commas

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

<start_of_turn>user

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

XMLSchema

-0.50

 darunter

-0.46

TypedDataSet

-0.45

GEBURTSDATUM

-0.44

 parmi

-0.43

ByPrimaryKey

-0.42

 cuar

-0.41

PositiveButton

-0.41

 comesti

-0.40

кож

-0.40

POSITIVE LOGITS

enterOuterAlt

0.48

seamnă

0.47

complexContent

0.46

 Chwiliwch

0.44

setVerticalGroup

0.42

WebControls

0.40

RTGC

0.40

thâu

0.40

 Diretto

0.39

 ControllerBase

0.39

Activations Density 0.000%

punctuation usage, particularly commas

<start_of_turn>user

No Comments

No Known Activations