INDEX

Explanations

descriptions of abilities and transformations

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

Ability/skill (hacking, regenerate, paralyze)

np_acts-logits-general · gemini-2.0-flash

ability to hack anything

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Walkover

-0.56

 것이다

-0.53

>[]

-0.52

Tage

-0.51

 referenties

-0.50

 BorderRadius

-0.49

<bos>

-0.48

OCCURRED

-0.48

tadır

-0.48

tuce

-0.47

POSITIVE LOGITS

anything

0.67

 anything

0.65

easily

0.62

 تضيفلها

0.62

Anything

0.61

archiviato

0.61

 NSCoder

0.60

yntaxException

0.57

 easily

0.57

 Anything

0.57

Activations Density 0.421%

descriptions of abilities and transformations

Ability/skill (hacking, regenerate, paralyze)

ability to hack anything

No Comments

No Known Activations