INDEX

Explanations

programming code and related elements

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

HTML or XML attribute names

np_acts-logits-general · gemini-2.0-flash

XML string resource names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UserScript

-0.62

 utafitiHapana

-0.56

őz

-0.50

TestingModule

-0.47

 '\\;'

-0.46

 незавершена

-0.46

---*/

-0.45

Single

-0.45

GeneratedCode

-0.44

Filmografia

-0.44

POSITIVE LOGITS

:][

0.66

attr

0.65

—

0.63

 attribute

0.60

 AttributeSet

0.58

 android

0.54

celotti

0.54

uxxxx

0.53

évaluateur

0.52

attribute

0.52

Activations Density 0.077%

programming code and related elements

HTML or XML attribute names

XML string resource names

No Comments

No Known Activations