INDEX

Explanations

elements related to personal expression and unique experiences

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

ResumeLayout

-0.61

BeforeMethod

-0.60

mybatisplus

-0.59

<?

-0.58

 AssemblyTitle

-0.57

 GenerationType

-0.57

paksa

-0.56

SBATCH

-0.55

 overnight

-0.55

 IANS

-0.54

POSITIVE LOGITS

 thrilling

0.61

 memorable

0.61

 romantic

0.61

 exciting

0.61

 featured

0.59

 fascinating

0.57

 commemorative

0.57

 impressive

0.57

 enthusiasts

0.57

 commemorating

0.56

Activations Density 0.576%

elements related to personal expression and unique experiences

No Comments

No Known Activations