INDEX

Explanations

structures and data types related to programming or hardware definitions

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

URLException

-0.64

 EClass

-0.54

 mouseY

-0.49

alogen

-0.48

lahraga

-0.48

 fool

-0.47

Iro

-0.47

ifndef

-0.47

gettext

-0.47

 SafeMath

-0.46

POSITIVE LOGITS

MLLoader

0.80

chartInstance

0.70

UnusedPrivate

0.69

ButterKnife

0.65

IContainer

0.65

ViewFeatures

0.63

ByExample

0.63

awaiter

0.63

 ViewHolder

0.59

TestBed

0.57

Activations Density 0.208%

structures and data types related to programming or hardware definitions

No Comments

No Known Activations