INDEX

Explanations

terms related to treatment protocols and health interventions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InjectAttribute

-0.81

 Infórmanos

-0.66

 للاسماء

-0.61

expandindo

-0.60

SourceChecksum

-0.56

TagMode

-0.56

 StatefulWidget

-0.55

MetaType

-0.54

RegisterType

-0.54

出版年

-0.53

POSITIVE LOGITS

 combinations

1.01

 combination

0.99

 Combination

0.84

combination

0.82

 combo

0.81

 consisting

0.80

Combination

0.80

combinations

0.79

mix

0.79

 Combinations

0.79

Activations Density 1.097%

terms related to treatment protocols and health interventions

No Comments

No Known Activations