INDEX

Explanations

comments and namespace declarations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 iste

-0.48

↵

-0.45

org

-0.45

</h3>

-0.45

bootstrapcdn

-0.43

Cyfeiriadau

-0.42

clerview

-0.42

gitto

-0.41

-0.40

POSITIVE LOGITS

tagHelperRunner

0.94

providedIn

0.92

 myſelf

0.87

 Anſ

0.87

BorderFactory

0.82

 Majefty

0.80

 viſ

0.79

 ་་

0.78

 ſever

0.77

 Conſ

0.76

Activations Density 0.056%

comments and namespace declarations in code

No Comments

No Known Activations