INDEX

Explanations

structured programming elements, such as function definitions and variable declarations

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

SpringBootTest

-0.58

expandindo

-0.58

]='\

-0.56

 فريبيس

-0.56

Portale

-0.53

esez

-0.53

 AppBundle

-0.52

tagHelperRunner

-0.51

 strto

-0.51

usepackage

-0.50

POSITIVE LOGITS

 index

2.25

index

1.98

 Index

1.96

Index

1.90

 indices

1.73

 INDEX

1.73

INDEX

1.72

 indexes

1.70

索引

1.66

 Indices

1.58

Activations Density 0.886%

structured programming elements, such as function definitions and variable declarations

No Comments

No Known Activations