INDEX

Explanations

references to utility classes and import statements in programming contexts

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

+#+

-0.68

enumi

-0.65

<bos>

-0.62

GraphicsUnit

-0.58

enumii

-0.56

VersionUID

-0.55

 consultato

-0.53

ParallelGroup

-0.51

 StatefulWidget

-0.50

’

-0.50

POSITIVE LOGITS

util

0.76

 flach

0.71

 विश्वसनीयता

0.71

 betweenstory

0.71

 Theſe

0.70

uſ

0.69

idious

0.67

ῆς

0.66

ViewFeatures

0.65

atists

0.65

Activations Density 0.025%

references to utility classes and import statements in programming contexts

No Comments

No Known Activations