INDEX

Explanations

phrases related to calculations and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

enterOuterAlt

-0.56

 newUser

-0.56



-0.53

 ProtoMessage

-0.53

newNode

-0.52

 newNode

-0.52

 imageName

-0.52

 accessToken

-0.52

glPopMatrix

-0.52

 newName

-0.51

POSITIVE LOGITS

 calculate

0.68

 determine

0.67

Calculate

0.66

 Calc

0.65

 Calculate

0.65

determine

0.64

calculate

0.63

Determine

0.62

calc

0.60

 Determine

0.60

Activations Density 0.340%

phrases related to calculations and algorithms

No Comments

No Known Activations