INDEX

Explanations

technical terms and instructions related to computer operations and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

पया

-0.56

adaptiveStyles

-0.52

AxisAlignment

-0.51

 registration

-0.50

 register

-0.50

 uska

-0.50

sidemargin

-0.50

sizeCache

-0.48

endaftaran

-0.48

 dAtA

-0.47

POSITIVE LOGITS

mov

0.62

mov

0.60

MOV

0.56

move

0.54

AutoScale

0.53

 comuniques

0.52

MOV

0.51

Move

0.51

 Konzert

0.51

Chham

0.50

Activations Density 0.514%

technical terms and instructions related to computer operations and programming

No Comments

No Known Activations