INDEX

Explanations

phrases indicating uncertainty or different possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IntoConstraints

-0.68

sizeCache

-0.59

ArgumentParser

-0.56

SuspendLayout

-0.55

TabIndex

-0.54

hige

-0.54

styleable

-0.52

createServer

-0.52

EnableWeb

-0.52

 specifically

-0.52

POSITIVE LOGITS

 comunque

0.82

 Regardless

0.80

总之

0.78

Regardless

0.76

反正

0.69

 uiteindelijk

0.64

Anyway

0.63

 regardless

0.63

 Anyway

0.62

 anyhow

0.62

Activations Density 0.296%

phrases indicating uncertainty or different possibilities

No Comments

No Known Activations