INDEX

Explanations

error handling statements and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

Espèce

-0.47

perti

-0.46

(&:

-0.46

Nasc

-0.45

idiary

-0.45

 fortification

-0.44

 medel

-0.43

antit

-0.43

 Seni

-0.43

AddHtmlAttribute

-0.42

POSITIVE LOGITS

FXMLLoader

0.81

webElementXpaths

0.69

ConfigureAwait

0.67

ⓧ

0.65

=$?

0.63

rrggbb

0.62

NameInMap

0.61

 EnglishChoose

0.61

 ISNI

0.60

GraphicsUnit

0.60

Activations Density 0.159%

error handling statements and conditions

No Comments

No Known Activations