INDEX

Explanations

terms related to names and titles associated with places or entities

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

CodeAttribute

-0.62

HomeAsUpEnabled

-0.57

MigrationBuilder

-0.53

apimachinery

-0.51

BIL

-0.51

WithEmail

-0.50

āng

-0.49

SqlClient

-0.48

tagena

-0.48

 Erişim

-0.48

POSITIVE LOGITS

 named

0.88

 naming

0.83

 namesake

0.83

named

0.80

 Named

0.77

naming

0.75

 Naming

0.72

 commemorative

0.71

 posthum

0.70

 commemor

0.70

Activations Density 0.168%

terms related to names and titles associated with places or entities

No Comments

No Known Activations