INDEX

Explanations

terms and phrases related to health, therapy, and treatment efficacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 οποία

-0.79

ngdoc

-0.68

 hän

-0.65

CloseOperation

-0.65

 surla

-0.63

 оно

-0.63

 она

-0.61

DoubleQuotes

-0.61

 они

-0.60

 Including

-0.60

POSITIVE LOGITS

the

1.17

how

0.95

ably

0.91

 some

0.90

 those

0.90

fully

0.87

 what

0.85

ly

0.85

and

0.84

atively

0.83

Activations Density 1.342%

terms and phrases related to health, therapy, and treatment efficacy

No Comments

No Known Activations