INDEX

Explanations

references to programming constructs and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

(");

-0.53

unate

-0.53

 gereken

-0.52

 ویکی‌پدیای

-0.48

CPtr

-0.48

 comigo

-0.48

 Offisielt

-0.47

 laikā

-0.47

 woorden

-0.46

tembre

-0.46

POSITIVE LOGITS

MessageTagHelper

0.78

 BoxDecoration

0.77

astify

0.75

 EconPapers

0.73

protoimpl

0.70

 BoxFit

0.68

BeginInit

0.66

évaluateur

0.66

 wireType

0.60

EndInit

0.59

Activations Density 1.076%

references to programming constructs and data types

No Comments

No Known Activations