INDEX

Explanations

terms related to academic or technical classifications

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

Aiheesta

-0.51

 createState

-0.47

ără

-0.47

NX

-0.46

 more

-0.46

tr

-0.44

or

-0.43

GetAxis

-0.43

 Epidemiology

-0.42

 Physik

-0.42

POSITIVE LOGITS

 EconPapers

0.82

HideFlags

0.80

MigrationBuilder

0.78

 للاسماء

0.73

 című

0.68

Gambas

0.68

 Cæsar

0.67

matchCondition

0.66

espé

0.66

."]

0.66

Activations Density 0.264%

terms related to academic or technical classifications

No Comments

No Known Activations