INDEX

Explanations

references to software errors or debugging messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 lenker

-0.60

esModule

-0.57

 AttributeSet

-0.54

 protoimpl

-0.54

 requestCode

-0.53

editary

-0.52

InputBorder

-0.52

didSet

-0.52

 getView

-0.51

onAttach

-0.51

POSITIVE LOGITS

RegressionTest

0.89

itinéraire

0.67

帖最后由

0.60

 betweenstory

0.57

Viited

0.56

}}}}

0.54

很快

0.54

 emiti

0.53

 بتاريخ

0.53

édrale

0.53

Activations Density 0.882%

references to software errors or debugging messages

No Comments

No Known Activations