INDEX

Explanations

terms related to medical and health concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 vulgaires

-0.75

PreferredItem

-0.74

SharedCtor

-0.73

 GenerationType

-0.69

 kasarigan

-0.68

 MainAxisSize

-0.64

 ExecuteAsync

-0.61

 فريبيس

-0.61

равда

-0.59

 nakalista

-0.59

POSITIVE LOGITS

 refers

1.07

 defined

1.02

any

0.91

defined

0.90

 term

0.89

 inaczej

0.87

Defined

0.84

 aquel

0.82

 aquella

0.82

Any

0.80

Activations Density 0.528%

terms related to medical and health concepts

No Comments

No Known Activations