INDEX

Explanations

numerical data and references related to machine learning and its applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 CURIAM

-0.50

 <=",

-0.50

Rujuakan

-0.49

 <<<<<<<<<<<<<<

-0.49

 retrou

-0.48

 onCancelled

-0.48

RenderAtEndOf

-0.47

انيف

-0.46

 sanitaires

-0.44

[]:

-0.44

POSITIVE LOGITS

Efq

0.64

 &___

0.64

følgelig

0.63

lapsingToolbar

0.63

WithIOException

0.59

kmale

0.59

 הזה

0.58

 OMITTED

0.57

ckså

0.56

genheim

0.56

Activations Density 0.032%

numerical data and references related to machine learning and its applications

No Comments

No Known Activations