INDEX

Explanations

the preposition "into."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AAS

-0.70

ScopeManager

-0.70

ษา

-0.68

 Moors

-0.67

yii

-0.67

 Calvo

-0.65

 âgées

-0.64

mallow

-0.64

 bier

-0.63

CEC

-0.62

POSITIVE LOGITS

 into

2.56

 INTO

2.26

 Into

2.25

Into

2.18

into

2.00

INTO

1.88

 onto

1.45

intos

0.96

 vào

0.95

onto

0.92

Activations Density 0.084%

the preposition "into."

No Comments

No Known Activations