INDEX

Explanations

programming constructs and coding syntax, particularly related to templates and namespaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Geplaatst

-0.81

DeleteBehavior

-0.79

Sucesor

-0.77

 pinulongan

-0.74

parsedMessage

-0.71

تقاوى

-0.69

StructEnd

-0.68

 Exacts

-0.67

 Roskov

-0.67

+#+#

-0.67

POSITIVE LOGITS

<bos>

0.68

Vidite

0.57

 MonoBehaviour

0.56

Port

0.52

 secco

0.51

Mutagenicity

0.50

iostream

0.50

maxn

0.48

;->

0.47

ennai

0.46

Activations Density 1.010%

programming constructs and coding syntax, particularly related to templates and namespaces

No Comments

No Known Activations