INDEX

Explanations

references to future actions or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

addPreferredGap

-0.73

 CommonModule

-0.71

новниш

-0.70

 Obrador

-0.70

 Cardigan

-0.69

 bandera

-0.66

 Censo

-0.66

voerd

-0.66

nesty

-0.66

 dissonance

-0.65

POSITIVE LOGITS

FUTURE

1.44

 future

1.43

 FUTURE

1.40

 Future

1.37

tableFuture

1.33

future

1.30

Future

1.30

 futura

1.21

 futures

1.12

avenir

1.12

Activations Density 0.059%

references to future actions or implications

No Comments

No Known Activations