INDEX

Explanations

references to specific models and products in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

featureID

-0.95

Personensuche

-0.73

SpringBootTest

-0.69

IVEREF

-0.67

twimg

-0.65

MethodManager

-0.61

MigrationBuilder

-0.60

BagConstraints

-0.60

rrggbb

-0.60

 незавершена

-0.60

POSITIVE LOGITS

 serisi

0.67

 fumée

0.63

series

0.62

 Majefty

0.61

Series

0.59

 ſhould

0.58

 series

0.58

 típus

0.57

 twos

0.56

 Diſ

0.56

Activations Density 0.422%

references to specific models and products in technology

No Comments

No Known Activations