INDEX

Explanations

the starting token of the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Princip

-0.55

المراجع

-0.54

JspWriter

-0.54

Autowired

-0.53

IRP

-0.52

Te

-0.52

moke

-0.52

TDG

-0.50

eqn

-0.50

ichtliche

-0.50

POSITIVE LOGITS

 للاسماء

0.77

 MenuView

0.77

onOptions

0.73

 autorytatywna

0.70

 AssemblyVersion

0.70

 ComVisible

0.69

 AssemblyProduct

0.68

ViewFeatures

0.67

AutoresizingMask

0.67

 resourceCulture

0.67

Activations Density 0.045%

the starting token of the document

No Comments

No Known Activations