INDEX

Explanations

terms and phrases related to properties and their configurations in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

kovou

-0.61

 Parigi

-0.59

ValueStyle

-0.57

doria

-0.50

 Оно

-0.49

 ब्रेकडाउन

-0.48

ագրություններ

-0.48

 alatt

-0.47

cích

-0.47

 betweenstory

-0.46

POSITIVE LOGITS

asantry

0.47

chatron

0.45

Див

0.44

 jeito

0.44

rimidine

0.43

ugier

0.43

 assunto

0.43

viously

0.43

 fato

0.43

 onAnimation

0.42

Activations Density 0.022%

terms and phrases related to properties and their configurations in a programming context

No Comments

No Known Activations