INDEX

Explanations

references to collaborations and contributors in scientific or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 obicei

-0.44

 ModelExpression

-0.44

entuh

-0.43

 DEFENSE

-0.43

kton

-0.42

 Smal

-0.41

 Loaf

-0.41

eader

-0.41

 culturelles

-0.41

Practical

-0.41

POSITIVE LOGITS

AlterField

0.85

AutoField

0.85

 مشين

0.80

RenderAtEndOf

0.78

ResumeLayout

0.77

.*")]

0.75

__*/

0.69

VersionUID

0.66

scalatest

0.66

SpringRunner

0.66

Activations Density 0.162%

references to collaborations and contributors in scientific or academic contexts

No Comments

No Known Activations