INDEX

Explanations

terms related to programming or technical specifications, particularly emphasizing functions or capabilities of systems or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.46

ತಿ

-0.44

conhe

-0.44

-0.41

 vœux

-0.41

נם

-0.41

 notte

-0.41

IsString

-0.41

io

-0.40

 azar

-0.40

POSITIVE LOGITS

 ITIS

0.76

uced

0.76

esterday

0.72

WriteBarrier

0.71

BufferException

0.71

tableFuture

0.70

calyp

0.70

 betweenstory

0.69

uxxxx

0.69

delic

0.69

Activations Density 0.306%

terms related to programming or technical specifications, particularly emphasizing functions or capabilities of systems or components

No Comments

No Known Activations