INDEX

Explanations

keywords related to documentation, processes, and compliance within structured contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

crum

-0.50

 minOccurs

-0.44

 Leone

-0.41

 Republica

-0.41

oredCriteria

-0.41

áfrica

-0.41

alto

-0.40

Ecotoxicity

-0.40

 Wayback

-0.39

SB

-0.39

POSITIVE LOGITS

ⓧ

0.74

AnchorStyles

0.71

AutoScale

0.69

 gyhoeddwyd

0.65

Kanpo

0.64

WebElementEntity

0.63

glEnd

0.62

IUrlHelper

0.62

InvalidProtocol

0.61

enschappelijke

0.60

Activations Density 0.473%

keywords related to documentation, processes, and compliance within structured contexts

No Comments

No Known Activations