INDEX

Explanations

programming syntax related to function definitions and return statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

DriverManager

-0.52

 Marston

-0.46

vers

-0.45

 Вікіпе

-0.44

rsiniz

-0.44

…

-0.42

igl

-0.42

xer

-0.41

alea

-0.39

地的

-0.39

POSITIVE LOGITS

 مشين

0.90

 bezeichneter

0.85

+#+#

0.84

UnusedPrivate

0.83

 snippetHide

0.79

تقاوى

0.79

StoreMessageInfo

0.74

 AssemblyCulture

0.74

MemoryWarning

0.73

adaptiveStyles

0.72

Activations Density 0.192%

programming syntax related to function definitions and return statements

No Comments

No Known Activations