INDEX

Explanations

elements of code documentation and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Cyfeiriadau

-0.70

 resourceCulture

-0.67

XmlType

-0.62

PerformLayout

-0.60

 StringTokenizer

-0.59

QMetaType

-0.57

IVEREF

-0.56

Obrázky

-0.56

parsedMessage

-0.55

 SwiftUI

-0.55

POSITIVE LOGITS

setopt

0.65

spreis

0.64

foon

0.51

gridx

0.49

{}",

0.49

enumii

0.48

 Cronin

0.48

("")]

0.48

 useAppContext

0.48

laceae

0.48

Activations Density 0.063%

elements of code documentation and annotations

No Comments

No Known Activations