INDEX

Explanations

numerical values and dates

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

Dates

np_acts-logits-general · gemini-2.0-flash

filenames and versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

WireFormatLite

-0.92

ChildScrollView

-0.81

complexContent

-0.65

tagext

-0.63

 EconPapers

-0.63

WriteBarrier

-0.60

urlpatterns

-0.59

ABU

-0.57

"]();

-0.57

OGND

-0.56

POSITIVE LOGITS

knapp

0.52

 فريبيس

0.44

legd

0.44

 gustar

0.43

IBinder

0.42

 traccia

0.42

 antworte

0.42

istemas

0.41

CURLOPT

0.41

ати

0.41

Activations Density 0.128%

numerical values and dates

Dates

filenames and versioning

No Comments

No Known Activations