INDEX

Explanations

technical terms and instructions related to computing and programming, specifically regarding CPU operations and assembly language

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

 nationally

-0.52

cyn

-0.52

فح

-0.50

 beste

-0.49

Viitteet

-0.48

 oleo

-0.48

Ear

-0.47

USET

-0.47

ichtet

-0.47

weigh

-0.47

POSITIVE LOGITS

 للاسماء

0.71

aarrggbb

0.67

InjectAttribute

0.64

ThroughAttribute

0.64

ImageContext

0.63

 GenerationType

0.63

 ControllerBase

0.62

WindowConstants

0.62

олові

0.62

ParallelGroup

0.62

Activations Density 0.525%

technical terms and instructions related to computing and programming, specifically regarding CPU operations and assembly language

No Comments

No Known Activations