INDEX

Explanations

references to the Apache library

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 cross

-0.62

 dung

-0.57

“

-0.55

↵↵

-0.53

 function

-0.52

ास्त

-0.52

 reco

-0.52

The

-0.51

 felt

-0.50

Lange

-0.50

POSITIVE LOGITS

AndEndTag

0.98

 enfans

0.96

Efq

0.91

 définiti

0.90

 ftate

0.83

fjspx

0.82

PerformLayout

0.81

RegistryLite

0.80

contentLoaded

0.79

 médicaux

0.78

Activations Density 0.576%

references to the Apache library

No Comments

No Known Activations