INDEX

Explanations

programming-related constructs, such as classes, templates, and method definitions

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

イルド

-0.58

baño

-0.57

 kiện

-0.57

>{@

-0.56

CDCl

-0.54

 Donahue

-0.54

심

-0.53

 campfire

-0.52

logrus

-0.52

Diwedd

-0.52

POSITIVE LOGITS

 Theſe

0.89

Efq

0.87

الإنجليزية

0.85

 Jefus

0.82

 itſelf

0.78

 AssemblyCulture

0.77

 Houſe

0.76

fjspx

0.76

 Beſ

0.76

 Monfieur

0.76

Activations Density 0.103%

programming-related constructs, such as classes, templates, and method definitions

No Comments

No Known Activations