INDEX

Explanations

technical terms and components related to programming and scientific processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

msgTypes

-0.87

TemporalType

-0.75

copg

-0.74

MessageTagHelper

-0.72

ViewImports

-0.72

parsedMessage

-0.72

 jScrollPane

-0.69

 IndexPath

-0.68

usercontent

-0.67

GraphicsUnit

-0.66

POSITIVE LOGITS

 passagers

0.55

 Lordships

0.52

 ferdig

0.51

 mukana

0.51

 niestety

0.51

⤹

0.50

 eorum

0.49

州市

0.48

YMMV

0.48

 niitä

0.48

Activations Density 1.584%

technical terms and components related to programming and scientific processes

No Comments

No Known Activations