INDEX

Explanations

keywords related to programming and compiler infrastructure, particularly LLVM's modules and passes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

出版年

-0.79

istoitu

-0.72

脚注の使い方

-0.65

defineProperty

-0.62

 resourceCulture

-0.60

RectangleBorder

-0.60

ThroughAttribute

-0.60

WebVitals

-0.57

AnchorStyles

-0.56

 للاسماء

-0.55

POSITIVE LOGITS

setVerticalGroup

0.56

RenderAtEndOf

0.54

žių

0.47

MLLoader

0.47

llingwood

0.47

 GameObject

0.46

StoredProcedure

0.45

rig

0.44

 uintptr

0.44

 rigs

0.43

Activations Density 1.029%

keywords related to programming and compiler infrastructure, particularly LLVM's modules and passes

No Comments

No Known Activations