INDEX

Explanations

references to the concept of "master" or "mastery"

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

 alimentaire

-0.75

emplos

-0.75

addColumn

-0.71

avion

-0.70

idends

-0.70

 Zwiebel

-0.68

 Scully

-0.68

 anticoag

-0.67

epam

-0.67

 suff

-0.65

POSITIVE LOGITS

 Masters

1.50

 masters

1.47

 MASTER

1.46

 Master

1.39

MASTER

1.35

 master

1.32

Masters

1.29

Master

1.27

master

1.19

masters

1.13

Activations Density 0.066%

references to the concept of "master" or "mastery"

No Comments

No Known Activations