INDEX

Explanations

code snippets related to system libraries and their components

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

 înc

-0.62

 picioare

-0.61

ItemBackground

-0.59

PreferredItem

-0.59

gantung

-0.58

leştir

-0.57

kulum

-0.56

 alluminio

-0.56

 Munch

-0.55

 partenza

-0.55

POSITIVE LOGITS

 BoxDecoration

0.94

 فريبيس

0.86

 estekak

0.74

tvguidetime

0.74

.*;

0.70

/**

0.69

 lenker

0.68

//

0.68

.*;

0.67

 برانيه

0.64

Activations Density 0.023%

code snippets related to system libraries and their components

No Comments

No Known Activations