INDEX

Explanations

code-related keywords and structures, particularly focusing on functions and variable definitions in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

FontOfSize

-0.73

ReusableCell

-0.62

amaño

-0.61

fromnode

-0.59

webElement

-0.57

OrNil

-0.55

BarStyle

-0.52

Marshaller

-0.52

 FontWeight

-0.51

POSITIVE LOGITS

 SafeMath

0.61

 AssemblyCompany

0.61

 utafitiHapana

0.59

 الحره

0.53

 HasFactory

0.48

LOTTE

0.48

Portály

0.47

 otomatig

0.47

gql

0.47

 checks

0.45

Activations Density 0.066%

code-related keywords and structures, particularly focusing on functions and variable definitions in programming languages

No Comments

No Known Activations