INDEX

Explanations

references to plates and food-related items

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

 GenerationType

-0.90

</tfoot>

-0.80

OrNil

-0.79

 onCancelled

-0.79

profen

-0.78

-0.76

 "'";

-0.73

appcompat

-0.72

']));

-0.72

utr

-0.72

POSITIVE LOGITS

 plates

1.79

 Plates

1.71

Plates

1.63

 Plate

1.61

 plate

1.59

 PLATES

1.53

 PLATE

1.52

plate

1.48

Plate

1.47

plates

1.46

Activations Density 0.093%

references to plates and food-related items

No Comments

No Known Activations