INDEX

Explanations

technical terminology and specific jargon related to programming or computer science

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

ending in "ter", "ite", "itic", "use"

np_acts-logits-general · gemini-2.0-flash

lateritic / laterites

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Autoritní

-0.69

 torchvision

-0.68

 Kidd

-0.64

copal

-0.63

BoxShadow

-0.63

طني

-0.62

 Griffin

-0.61

ագրություններ

-0.61

WireFormatLite

-0.61

Griffin

-0.61

POSITIVE LOGITS

AsUp

0.95

SupportActionBar

0.61

MeasureSpec

0.59

(()=>

0.54

 Justine

0.54

 Olympedia

0.52

 hiperten

0.52

 terk

0.52

InvalidProtocol

0.52

omla

0.51

Activations Density 1.009%

technical terminology and specific jargon related to programming or computer science

ending in "ter", "ite", "itic", "use"

lateritic / laterites

No Comments

No Known Activations