INDEX

Explanations

references to stages of classification or levels in medical conditions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

riwal

-0.84

CrossRef

-0.84

}')

-0.83

IsPostBack

-0.82

 Vienne

-0.81

ಿಸ

-0.78

Bik

-0.77

Bik

-0.77

<0xD4>

-0.76

POSITIVE LOGITS

 STAGE

1.37

 Stage

1.33

Stage

1.28

STAGE

1.27

stage

1.23

 stage

1.14

stages

1.13

Stages

1.13

 stages

1.11

 Stages

1.07

Activations Density 0.011%

references to stages of classification or levels in medical conditions or processes

No Comments

No Known Activations