INDEX

Explanations

phrases that describe conditions or instructions for tasks or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 pleaſure

-1.38

 Monfieur

-1.33

 Jefus

-1.32

Efq

-1.24

 faſt

-1.18

 Majefty

-1.17

 houſe

-1.16

 Chriftian

-1.14

 ſever

-1.14

 ſtate

-1.13

POSITIVE LOGITS

Чтобы

0.91

 inorder

0.91

 afin

0.87

 أجل

0.86

 Để

0.86

 чтобы

0.86

是为了

0.82

 Чтобы

0.81

 upang

0.78

 щоб

0.77

Activations Density 0.066%

phrases that describe conditions or instructions for tasks or processes

No Comments

No Known Activations