INDEX

Explanations

lines of code or programming constructs in a programming language context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Trim

-0.47

?>

-0.46

 NULL

-0.44

拉

-0.44

Westfalen

-0.43

 null

-0.42

?>

-0.42

 award

-0.42

 naturels

-0.41

ها

-0.41

POSITIVE LOGITS

tvguidetime

0.92

protoimpl

0.84

elemField

0.83

Vidite

0.81

styleType

0.80

Rüyada

0.78



0.77

 propOrder

0.76

 saites

0.75

RTDA

0.74

Activations Density 0.353%

lines of code or programming constructs in a programming language context

No Comments

No Known Activations