INDEX

Explanations

the references to the term "mi," likely signifying an important concept or element in the context

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

IsContent

-0.67

InputBorder

-0.64

شهاد

-0.62

TestingModule

-0.61

+#+

-0.59

 صوتيه

-0.58

enação

-0.56

DMETHOD

-0.55

odis

-0.55

LayoutStyle

-0.54

POSITIVE LOGITS

mi

3.04

mi

2.95

Mi

2.86

Mi

2.79

MI

2.43

MI

2.31

AMI

1.24

Mih

1.19

miu

1.17

 ми

1.14

Activations Density 0.028%

the references to the term "mi," likely signifying an important concept or element in the context

No Comments

No Known Activations