INDEX

Explanations

punctuation marks

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

CPtr

-0.58

 maximizes

-0.54

kháu

-0.52

 BorderRadius

-0.51

ADI

-0.51

 présidenti

-0.48

 Италијани

-0.48

 maximizing

-0.47

ADI

-0.47

quelles

-0.47

POSITIVE LOGITS

出版年

0.83

TabIndex

0.78

 مشين

0.74

 فريبيس

0.73

TagMode

0.72

mappedBy

0.68

ंदीखरीदारी

0.67

findpost

0.67

providedIn

0.67

componentDid

0.65

Activations Density 0.016%

punctuation marks

No Comments

No Known Activations