INDEX

Explanations

references to various services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

reactstrap

-0.78

 arşivlendi

-0.75

Oat

-0.71

 Walkover

-0.71

 Wachs

-0.71

AGU

-0.66

chequer

-0.65

 Nutt

-0.65

 Савезне

-0.64

Šaltiniai

-0.64

POSITIVE LOGITS

 services

2.26

 Services

2.04

Services

1.96

services

1.89

 SERVICES

1.84

SERVICES

1.74

ervices

1.59

 diensten

1.54

 servicios

1.38

 serviços

1.27

Activations Density 0.034%

references to various services

No Comments

No Known Activations