INDEX

Explanations

terms related to physical and mental health

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

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

})();

-0.76

artigen

-0.71

artige

-0.68

withIdentifier

-0.68

 Socialists

-0.66

 Danilo

-0.65

 שוליים

-0.65

 préfé

-0.65

HandlerContext

-0.63

 Shakspeare

-0.63

POSITIVE LOGITS

 Physical

1.04

 physical

0.98

Physical

0.98

 PHYSICAL

0.95

physical

0.90

PHYSICAL

0.89

 physically

0.76

phys

0.76

 phys

0.74

 физи

0.69

Activations Density 0.100%

terms related to physical and mental health

No Comments

No Known Activations