INDEX

Explanations

references to "Camp" in various contexts

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

"Camp" followed by a location or modifier

np_acts-logits-general · gemini-2.0-flash

camp followed by other words

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.74

 demand

-0.72

bootstrapcdn

-0.69

 Demand

-0.68

 للمعارف

-0.67

 demanda

-0.65

Demand

-0.64

исленность

-0.64

 الرياضيه

-0.62

izophrenia

-0.61

POSITIVE LOGITS

 camps

0.82

 CAMP

0.80

camp

0.78

Camp

0.77

 camp

0.72

 Camp

0.72

site

0.71

grounds

0.70

 Camps

0.68

fires

0.67

Activations Density 0.049%

references to "Camp" in various contexts

"Camp" followed by a location or modifier

camp followed by other words

No Comments

No Known Activations