INDEX

Explanations

phrases related to visual or auditory perception

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

RefNanny

-0.65

 vaso

-0.52

 tartalomajánló

-0.52

waffe

-0.51

期刊论文

-0.51

await

-0.50

WA

-0.49

 Reine

-0.48

tagHelperRunner

-0.47

ésor

-0.46

POSITIVE LOGITS

 AssemblyCulture

0.87

awtextra

0.82

idać

0.79

ftagPool

0.78

 فريبيس

0.76

 initComponents

0.75

 visibles

0.71

 <>",

0.70

addPreferredGap

0.68

BindView

0.67

Activations Density 0.133%

phrases related to visual or auditory perception

No Comments

No Known Activations