INDEX

Explanations

positive activation markers indicating the start of a section

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

 فريبيس

-0.70

Дереккөздер

-0.70

Tikang

-0.68

Rhestr

-0.66

guenos

-0.66

 صوتيه

-0.65

 ProtoMessage

-0.63

 Epistle

-0.62

IonicModule

-0.62

AddTagHelper

-0.61

POSITIVE LOGITS

 EconPapers

0.64

:"-"`

0.56

res

0.51

(&$

0.50

<h2>

0.50

sistant

0.50

javax

0.49

rzej

0.49

const

0.48

[]=$

0.48

Activations Density 0.011%

positive activation markers indicating the start of a section

No Comments

No Known Activations