INDEX

Explanations

references to specific functions or code syntax in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

SourceChecksum

-0.87

 Normdatei

-0.84

 nakalista

-0.76

hasMoreElements

-0.75

elemField

-0.73

 présidenti

-0.72

contentLoaded

-0.70

存于互联网档案馆

-0.68

featureID

-0.66

TypedDataSet

-0.64

POSITIVE LOGITS

fri

0.58

mybatisplus

0.58

autogui

0.56

Hen

0.52

Fri

0.52

 numberWith

0.51

nis

0.49

Fri

0.48

 MonoBehaviour

0.48

BeginContext

0.48

Activations Density 0.023%

references to specific functions or code syntax in programming

No Comments

No Known Activations