INDEX

Explanations

mathematical expressions and symbols associated with logical or computational concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ViewImports

-0.77

 credere

-0.72

Demografía

-0.68

ViewFeatures

-0.67

انيف

-0.67

 Roskov

-0.65

 aimez

-0.62

verwijspagina

-0.62

uxxxx

-0.62

 EconPapers

-0.56

POSITIVE LOGITS

XMLSchema

0.73

ezers

0.68

getElementById

0.68

//

0.67

––––

0.64

 Kreise

0.62

_('

0.60

 Abram

0.60

üglich

0.60

letoe

0.60

Activations Density 0.425%

mathematical expressions and symbols associated with logical or computational concepts

No Comments

No Known Activations