INDEX

Explanations

questions and relational phrases

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

 contextLoads

-0.90

jména

-0.87

 Majefty

-0.85

 Chriſt

-0.83

 Jefus

-0.80

empereur

-0.79

 tourisme

-0.78

 eſt

-0.78

 purpoſe

-0.78

 ſon

-0.78

POSITIVE LOGITS

que

1.24

Que

1.18

Que

1.18

QUE

1.00

że

0.95

que

0.91

že

0.85

Qui

0.83

Qui

0.82

 hogy

0.81

Activations Density 0.024%

questions and relational phrases

No Comments

No Known Activations