INDEX

Explanations

various instances of structured data or code-related elements

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.57

 Waray

-0.56

 isInitialized

-0.50

OnTop

-0.48

 '\\;'

-0.48

клопе

-0.48

openzeppelin

-0.47

Externé

-0.47

Selectable

-0.46

 multiplier

-0.46

POSITIVE LOGITS

Попис

0.62

tvguidetime

0.55

gulier

0.54

tgl

0.52

 HasFactory

0.51

IsContent

0.50

ír

0.50

({},

0.50

 transfieras

0.48

InvalidProtocol

0.48

Activations Density 0.219%

various instances of structured data or code-related elements

No Comments

No Known Activations