INDEX

Explanations

references to "sand" and its various forms or contexts

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

"Sand" or similar

np_acts-logits-general · gemini-2.0-flash

sand followed by a word

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Referanser

-0.63

 déri

-0.56

 betweenstory

-0.56

 Alonzo

-0.56

Obrázky

-0.54

PhysRevD

-0.53

 وتسجيلات

-0.53

<%=

-0.52

idemia

-0.52

schild

-0.51

POSITIVE LOGITS

wic

0.98

 Sand

0.97

Sand

0.92

 SAND

0.91

SAND

0.83

 sand

0.83

 Sanderson

0.79

 dunes

0.79

 Sanders

0.78

 zand

0.77

Activations Density 0.049%

references to "sand" and its various forms or contexts

"Sand" or similar

sand followed by a word

No Comments

No Known Activations