INDEX

Explanations

words and patterns related to names and titles

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

__':

-0.56

else

-0.54

 financières

-0.52

GraphicsUnit

-0.50

HasBeenSet

-0.49

LinkId

-0.48

stdc

-0.47

NegativeButton

-0.46

 مشين

-0.45

ěli

-0.45

POSITIVE LOGITS

]--;

0.65

Примечания

0.63

 spørs

0.58

HKEY

0.56

atric

0.55

Atsauces

0.54

keyDown

0.53

 Sarm

0.53

holdet

0.53

DTD

0.53

Activations Density 0.944%

words and patterns related to names and titles

No Comments

No Known Activations