INDEX

Explanations

direct quotes or paragraphs with attribution

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

Punctuation after certain words

np_acts-logits-general · gemini-2.0-flash

contextual punctuation and conjunctions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 solcher

-0.42

countryCode

-0.40

^(@)

-0.40

toThrow

-0.39

 COVID

-0.39

cvtColor

-0.39

destroyAll

-0.39

imgdir

-0.38

gebir

-0.37

spaceBetween

-0.37

POSITIVE LOGITS

contentLoaded

0.54

 EconPapers

0.49

ArrowToggle

0.48

uesia

0.46

 OkHttpClient

0.45

 NSCoder

0.43

CloseOperation

0.42

хьтан

0.42

GenerationType

0.41

galkan

0.41

Activations Density 2.126%

direct quotes or paragraphs with attribution

Punctuation after certain words

contextual punctuation and conjunctions

No Comments

No Known Activations