INDEX

Explanations

phrases that indicate causes or attributes related to phenomena or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

yntaxException

-0.72

ագրություններ

-0.67

<?

-0.65

findpost

-0.63

Obrázky

-0.63

 متعلقه

-0.62

 صوتيه

-0.61

endphp

-0.59

Hauptartikel

-0.56

">//

-0.55

POSITIVE LOGITS

due

0.76

 reasons

0.71

 because

0.68

due

0.68

 disebabkan

0.66

 factores

0.64

 attributable

0.64

reasons

0.64

 factors

0.64

 REASONS

0.63

Activations Density 0.457%

phrases that indicate causes or attributes related to phenomena or observations

No Comments

No Known Activations