INDEX

Explanations

phrases related to initiating actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

MutableLiveData

-0.51

forName

-0.45

appendChild

-0.44

 jSON

-0.44

 ArrayAdapter

-0.44

xer

-0.43

 externi

-0.42

 polega

-0.42

таратура

-0.42

 ulcers

-0.42

POSITIVE LOGITS

 starters

0.96

 starter

0.95

 start

0.89

starter

0.88

 prelude

0.86

 Starter

0.86

 introductory

0.82

 beginning

0.81

 Start

0.81

Starter

0.79

Activations Density 0.188%

phrases related to initiating actions or processes

No Comments

No Known Activations