INDEX

Explanations

quantitative descriptions related to health metrics or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

tagHelperRunner

-0.61

gas

-0.55

 disponibilités

-0.54

FFIX

-0.54

sass

-0.51

SAS

-0.50

sas

-0.48

RDONLY

-0.48

 AudioSource

-0.48

 Cass

-0.47

POSITIVE LOGITS

0.76

rungsseite

0.67

[*]

0.66

BeginContext

0.61

titleMargin

0.57

hotel

0.56

 chung

0.56

IsContent

0.54

});*/

0.52

 hotelu

0.51

Activations Density 0.130%

quantitative descriptions related to health metrics or measurements

No Comments

No Known Activations