INDEX

Explanations

references to annual events or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

//

-0.56

 ecuator

-0.51

 ekor

-0.48

 ammat

-0.46

 alguna

-0.46

feather

-0.44

gouv

-0.44

 tham

-0.44

degard

-0.44

 thiệu

-0.43

POSITIVE LOGITS

MigrationBuilder

0.99

expandindo

0.88

 betweenstory

0.78

DeleteBehavior

0.78

__':

0.73

 annuel

0.73

addContainerGap

0.71

Rhestr

0.71

AddTagHelper

0.71

ized

0.71

Activations Density 0.076%

references to annual events or reports

No Comments

No Known Activations