INDEX

Explanations

references to parameters in discussions or descriptions of systems or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AttributeSet

-0.52

BeginInit

-0.51

 Evita

-0.50

 tail

-0.47

uity

-0.46

AttributeSet

-0.45

Exact

-0.45

 Faker

-0.45

dify

-0.44

PerformLayout

-0.44

POSITIVE LOGITS

 parameter

0.89

 parameters

0.81

param

0.73

参数

0.72

 parámetros

0.69

 Parameter

0.68

Parameter

0.67

parameter

0.66

 param

0.66

parameters

0.62

Activations Density 0.275%

references to parameters in discussions or descriptions of systems or functions

No Comments

No Known Activations