INDEX

Explanations

functions related to loading or initialization processes in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 الرياضيه

-0.68

 CURIAM

-0.59

CloseOperation

-0.58

rungsseite

-0.57

RotationOrder

-0.56

 Rigidbody

-0.56

tangentMode

-0.56

المكان

-0.55

 Walkover

-0.54

舺

-0.54

POSITIVE LOGITS

load

1.13

Load

0.83

LOAD

0.76

 Load

0.54

 hire

0.52

 hires

0.50

 Hire

0.47

SetUp

0.45

Hire

0.44

Init

0.44

Activations Density 0.137%

functions related to loading or initialization processes in code

No Comments

No Known Activations