INDEX

Explanations

specific programming structures and expressions related to data manipulation and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ویکی‌پدیا

-0.66

 kasarigan

-0.64

<bos>

-0.63

ParallelGroup

-0.60

BeginContext

-0.60

ंदीखरीदारी

-0.60

 cardíaca

-0.59

ConstraintMaker

-0.58

paroles

-0.57

InjectAttribute

-0.57

POSITIVE LOGITS

ﷺ

0.57

 himself

0.55

RenderAtEndOf

0.55

orie

0.49

 herself

0.48

endphp

0.48

 themselves

0.47

yles

0.47

csolódó

0.46

Allister

0.46

Activations Density 1.158%

specific programming structures and expressions related to data manipulation and calculations

No Comments

No Known Activations