INDEX

Explanations

references to academic publications and datasets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

""".

-0.52

AndEndTag

-0.51

the

-0.49

scalatest

-0.49

and

-0.48

Πηγές

-0.47

vode

-0.47

 <<<<<<<<<<<<<<

-0.46

or

-0.46

cydow

-0.46

POSITIVE LOGITS

FontOfSize

0.76

 photolibrary

0.72

 Shakspeare

0.71

DeleteBehavior

0.71

 ainfi

0.71

CloseOperation

0.68

 referenties

0.67

 TextInputType

0.66

 Finlay

0.63

躇

0.62

Activations Density 0.675%

references to academic publications and datasets

No Comments

No Known Activations