INDEX

Explanations

references to services or support-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.31

 Monfieur

-1.25

 Anſ

-1.22

 Theſe

-1.20

 myſelf

-1.20

Efq

-1.19

 Majefty

-1.13

 Jefus

-1.11

 themſelves

-1.10

 Reſ

-1.10

POSITIVE LOGITS

 Services

1.03

services

0.99

Services

0.95

 services

0.93

 SERVICES

0.79

SERVICES

0.68

0.60

0.58

↵↵

0.57

tr

0.57

Activations Density 0.116%

references to services or support-related topics

No Comments

No Known Activations