INDEX

Explanations

terms related to methods and properties in scientific or technical 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

#+#

-0.74

tagHelperRunner

-0.65

 Meksiku

-0.64

SourceChecksum

-0.63

principalTable

-0.63

__*/

-0.62

addCriterion

-0.60

EDEFAULT

-0.59

 سكانية

-0.58

iNdEx

-0.58

POSITIVE LOGITS

 edildi

0.48

dois

0.42

AutoField

0.41

 selected

0.41

ęż

0.40

select

0.40

 Redewendung

0.40

 select

0.39

Pyx

0.39

ècie

0.38

Activations Density 0.925%

terms related to methods and properties in scientific or technical contexts

No Comments

No Known Activations