INDEX

Explanations

mentions of the word "card"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 uſed

-0.77

出版年

-0.64

setzt

-0.63

gnu

-0.62

didSet

-0.60

 ""],

-0.60

 agrícolas

-0.59

 becauſe

-0.59

 myſelf

-0.59

]}

-0.59

POSITIVE LOGITS

card

4.56

 card

4.45

Card

4.38

 Card

4.38

 CARD

3.83

CARD

3.69

 cards

3.61

 Cards

3.55

cards

3.47

Cards

3.35

Activations Density 0.066%

mentions of the word "card"

No Comments

No Known Activations