INDEX

Explanations

phrases indicating personal involvement or experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

/***/

-0.56

PyTuple

-0.52

 disponibilités

-0.49

CPR

-0.48

िल्

-0.48

bobox

-0.47

रीदारी

-0.47

 Frit

-0.46

 EconPapers

-0.46

 allusions

-0.45

POSITIVE LOGITS

jun

1.09

JUN

1.06

Jun

1.01

Jun

1.00

jun

0.89

 junk

0.86

ChildScrollView

0.83

 Junk

0.82

 AssemblyTitle

0.81

JUN

0.80

Activations Density 0.144%

phrases indicating personal involvement or experience

No Comments

No Known Activations