INDEX

Explanations

programming constructs and keywords related to data processing and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 noDo

-0.60

VYMaps

-0.56

 protoimpl

-0.55

 estekak

-0.52

PyExc

-0.52

 EconPapers

-0.51

ValueStyle

-0.51

المناصب

-0.51

IsMutable

-0.50

IntoConstraints

-0.50

POSITIVE LOGITS

 tarvit

0.39

 fantasmas

0.39

artificial

0.37

 resultó

0.37

 companhia

0.36

 fantasma

0.35

 aliados

0.35

 ternyata

0.35

 imaginar

0.35

 investasi

0.34

Activations Density 0.384%

programming constructs and keywords related to data processing and manipulation

No Comments

No Known Activations