INDEX

Explanations

quantitative comparisons and measurements related to medical or statistical data

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Happy

-0.51

ništvo

-0.50

Sha

-0.47

strpos

-0.47

putBoolean

-0.47

onAttach

-0.46

AutoField

-0.46

happy

-0.46

maketitle

-0.45

‘

-0.45

POSITIVE LOGITS

webElementGuid

0.72

 wikipagina

0.69

PMailer

0.68

ConstraintMaker

0.67

 pinulongan

0.64

TagMode

0.62

 desconhe

0.62

 estre

0.61

 desconoc

0.60

zaamheid

0.60

Activations Density 0.858%

quantitative comparisons and measurements related to medical or statistical data

No Comments

No Known Activations