INDEX

Explanations

proper nouns and significant names

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

 Colton

-0.74

le

-0.72

ing

-0.71

Pierre

-0.70

de

-0.69

 chicos

-0.69

 Pires

-0.69

da

-0.68

tabria

-0.64

 Norwood

-0.64

POSITIVE LOGITS

Sucesor

1.03

findpost

1.02

 Imper

1.02

Hauptartikel

1.01

 виправивши

0.95

 AssemblyCulture

0.95

 Jacobs

0.94

Jacobs

0.93

Bez

0.92

 Krav

0.91

Activations Density 0.638%

proper nouns and significant names

No Comments

No Known Activations