INDEX

Explanations

references to specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 doInBackground

-0.52



-0.45

WaitGroup

-0.45

itinéraire

-0.44

 élevées

-0.43

 sauvages

-0.42

MessageTagHelper

-0.41

êng

-0.41

CloseOperation

-0.41

empereur

-0.40

POSITIVE LOGITS

 office

2.86

 offices

2.63

office

2.41

 Office

2.17

 OFFICE

2.12

 Offices

2.12

offices

2.09

Office

2.07

OFFICE

1.89

 oficina

1.80

Activations Density 0.263%

references to specific locations and institutions

No Comments

No Known Activations