INDEX

Explanations

numerical values and mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Wikimedijinoj

-0.57

 noqa

-0.57

mybatisplus

-0.54

RenderAtEndOf

-0.54

 SIMBAD

-0.51

 kasarigan

-0.51

 ddelweddau

-0.50

 patin

-0.50

 centrif

-0.48

inhard

-0.48

POSITIVE LOGITS

AndEndTag

0.70

لينكات

0.60

discriminator

0.53

 CGRectMake

0.52

 Lerner

0.52

навли

0.51

DockStyle

0.51

estacks

0.51

angana

0.50

 InputDecoration

0.50

Activations Density 0.046%

numerical values and mathematical expressions

No Comments

No Known Activations