INDEX

Explanations

starting points or introductions to new sections or topics in text

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

after company or organization names

np_acts-logits-general · gemini-2.0-flash

legal, technical, or financial phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

行政区划

-0.61

Geplaatst

-0.53

:✨

-0.52

untergang

-0.52

 coloré

-0.52

 "..\..\

-0.49

 ObjectMapper

-0.49

ianas

-0.48

estacks

-0.47

بوابة

-0.47

POSITIVE LOGITS

DataAnnotations

0.57

leps

0.53

ChildScrollView

0.53

RUnlock

0.53

 carbon

0.50

belongs

0.50

HtmlAttribute

0.50

 Toulon

0.49

AxisAlignment

0.49

principalColumn

0.48

Activations Density 0.059%

starting points or introductions to new sections or topics in text

after company or organization names

legal, technical, or financial phrases

No Comments

No Known Activations