INDEX

Explanations

references to technical terms, processes, and methods related to data modeling and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Esk

-0.70

 Monaghan

-0.70

Nog

-0.69

 Higgins

-0.67

 banana

-0.67

 Ascot

-0.67

 Poplar

-0.66

 bananas

-0.65

 Fabio

-0.62

 Wiley

-0.62

POSITIVE LOGITS

 Chamb

0.91

 Dickinson

0.90

 CHAM

0.87

 Chambers

0.85

itz

0.82

 Seitz

0.79

 Chak

0.79

Cha

0.78

 Chavez

0.78

CHAM

0.78

Activations Density 1.790%

references to technical terms, processes, and methods related to data modeling and analysis

No Comments

No Known Activations