INDEX

Explanations

terms related to prevention in health contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

leſs

-0.63

 tranſ

-0.49

 raiſ

-0.45

 UserDao

-0.42

_('

-0.41

KommentareTeilen

-0.39

 obſ

-0.39

 femininas

-0.39

 asim

-0.39

 themſelves

-0.38

POSITIVE LOGITS

XmlAccessorType

0.68

 techniques

0.65

github

0.59

 برانيه

0.57

 Techniques

0.57

Techniques

0.56

techniques

0.55

 ProtoMessage

0.53

èdia

0.53

 technique

0.53

Activations Density 0.205%

terms related to prevention in health contexts

No Comments

No Known Activations