INDEX

Explanations

terms related to protective health behaviors and medical treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

MLLoader

-0.63

httphttps

-0.61

 '\\;'

-0.60

ArgsConstructor

-0.59

 насељу

-0.59

ValueStyle

-0.58

UIControlState

-0.55

oneofs

-0.54

ьажоргаш

-0.52

sidemargin

-0.51

POSITIVE LOGITS

 protection

1.09

 protective

1.04

 protecting

0.97

 protect

0.91

 Protection

0.90

Protection

0.89

Protective

0.88

protection

0.86

 Protective

0.85

 protección

0.83

Activations Density 1.512%

terms related to protective health behaviors and medical treatments

No Comments

No Known Activations