INDEX

Explanations

references to various types of services

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

IntoConstraints

-0.93

Efq

-0.90

 doubtnut

-0.87

 UNHCR

-0.86

 Majefty

-0.86

 monasteries

-0.82

 poffible

-0.82

 himſelf

-0.82

 Partagez

-0.81

 fhort

-0.80

POSITIVE LOGITS

 service

3.74

 Service

3.30

service

3.08

Service

3.00

 SERVICE

2.96

SERVICE

2.78

 services

2.63

ervice

2.47

 servicio

2.42

 Services

2.25

Activations Density 0.048%

references to various types of services

No Comments

No Known Activations