INDEX

Explanations

key phrases or elements indicating change or transition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

pre

-0.43

ici

-0.42

che

-0.41

com

-0.41

к

-0.40

Com

-0.39

de

-0.39

-0.37

za

-0.37

POSITIVE LOGITS

 itſelf

1.36

 indeed

1.33

 finalement

1.24

 inderdaad

1.23

 Anſ

1.18

 myſelf

1.17

 Majefty

1.16

 Monfieur

1.15

 ſche

1.11

 faſt

1.11

Activations Density 0.267%

key phrases or elements indicating change or transition

No Comments

No Known Activations