INDEX

Explanations

elements related to GPU architecture and specifications

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

graphics cards or GPUs

np_acts-logits-general · gemini-2.0-flash

graphics card

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 surla

-0.65

BASEPATH

-0.61

Law

-0.60

醐

-0.59

 probiotics

-0.57

alarm

-0.55

 alarm

-0.53

SPATH

-0.53

 jang

-0.53

addPreferredGap

-0.53

POSITIVE LOGITS

 graphics

1.05

GPU

1.00

 Graphics

0.92

 GPUs

0.85

 Nvidia

0.84

 NVIDIA

0.83

 GeForce

0.83

 nvidia

0.82

Graphics

0.82

gpu

0.81

Activations Density 0.232%

elements related to GPU architecture and specifications

graphics cards or GPUs

graphics card

No Comments

No Known Activations