INDEX

Explanations

concluding tags or end indicators in a structured document

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

<end_of_turn> token

np_acts-logits-general · gemini-2.0-flash

code structures and UI elements

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Cred

-0.45

weightedMode

-0.45

PMailer

-0.45

titian

-0.43

eynman

-0.43

 themſelves

-0.43

 Bourgoin

-0.43

itempty

-0.42

$_(

-0.42

lusconi

-0.42

POSITIVE LOGITS

RegressionTest

0.69

 <=",

0.56

LayoutStyle

0.54

EndContext

0.49

queryInterface

0.47

ChildScrollView

0.44

 <<<<<<<<<<<<<<

0.44

jspx

0.40

UseVisualStyle

0.37

IntoConstraints

0.37

Activations Density 0.770%

concluding tags or end indicators in a structured document

<end_of_turn> token

code structures and UI elements

No Comments

No Known Activations