INDEX

Explanations

references to numerical data or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

はじめに

-0.74

 <<<<<<<<<<<<<<

-0.60

TagMode

-0.58

 становника

-0.53

nalités

-0.52

 panoramique

-0.51

 efectivamente

-0.51

 StatefulWidget

-0.50

 مرئيه

-0.48

ConstraintMaker

-0.48

POSITIVE LOGITS

 meanwhile

0.93

 others

0.80

 other

0.77

 conversely

0.75

else

0.72

Conversely

0.70

others

0.70

Others

0.69

omiast

0.68

 later

0.68

Activations Density 0.464%

references to numerical data or quantities

No Comments

No Known Activations