INDEX

Explanations

code snippets related to auto-generated methods or events 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 redistribute

-0.67

cisive

-0.65

ladiator

-0.59

usahaan

-0.58

wahlen

-0.58

 Distributions

-0.58

 ferroviaire

-0.58

AlterField

-0.57

 Stabilization

-0.57

ruptcy

-0.56

POSITIVE LOGITS

ArgsConstructor

1.61

HomeAsUpEnabled

0.86

gms

0.83

addComponent

0.82

MemoryWarning

0.81

awtextra

0.81

//}

0.75

 nahilalakip

0.73

󠁢

0.69

kuuta

0.65

Activations Density 0.005%

code snippets related to auto-generated methods or events in programming

No Comments

No Known Activations