INDEX

Explanations

phrases or terms related to roles and duties within authority or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UELA

-0.57

lojik

-0.52

 experimenter

-0.51

 insensible

-0.48

 crutches

-0.48

 Lewin

-0.48

MessageTagHelper

-0.48

 imprim

-0.47

clist

-0.47

 étu

-0.47

POSITIVE LOGITS

 role

1.49

 roles

1.43

 duties

1.30

 rôle

1.23

 Roles

1.18

 Role

1.16

 Aufgaben

1.14

 ROLE

1.13

role

1.12

 Duties

1.09

Activations Density 0.379%

phrases or terms related to roles and duties within authority or organizations

No Comments

No Known Activations