INDEX

Explanations

programming-related keywords and structures within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.50

oredCriteria

-0.48

WebElementEntity

-0.45

PerformLayout

-0.41

UserScript

-0.40

 setEmail

-0.40

cashire

-0.39

HasAnnotation

-0.39

bleau

-0.38

GTCX

-0.38

POSITIVE LOGITS

CloseOperation

0.59

OGND

0.47

 Mustafa

0.46

 Acero

0.43

 Aseg

0.43

Enllaces

0.41

beding

0.41

 Atlántico

0.41

 pinulongan

0.41

 Debido

0.40

Activations Density 0.066%

programming-related keywords and structures within code snippets

No Comments

No Known Activations