INDEX

Explanations

programming-related concept references within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyProduct

-0.63

justed

-0.61

__':

-0.61

batore

-0.59

 iconTwitter

-0.58

 Hän

-0.58

rões

-0.57

zufügen

-0.57

lloworld

-0.56

 مفص

-0.56

POSITIVE LOGITS

printStackTrace

0.51

 Einf

0.49

 Orts

0.48

DoubleQuotes

0.47

ElementException

0.46

keyColumn

0.46

 fahr

0.46

AnimationsModule

0.44

!("{}",

0.43

DropTable

0.42

Activations Density 0.116%

programming-related concept references within code

No Comments

No Known Activations