INDEX

Explanations

code structure elements, such as function and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ArrowToggle

-0.47

 gyhoeddwyd

-0.45

verwijspagina

-0.44

astify

-0.44

 энциклопедия

-0.37

astéroïdes

-0.35

kiksi

-0.35

 häl

-0.35

Pautan

-0.35

 scarpe

-0.34

POSITIVE LOGITS

发表于

0.48

SPJ

0.47

earcher

0.46

 namelijk

0.44

 GenerationType

0.44

endregion

0.43

 صوتيه

0.43

KS

0.42

 numberWith

0.42

ItemBackground

0.41

Activations Density 0.160%

code structure elements, such as function and class definitions

No Comments

No Known Activations