INDEX

Explanations

references to data presentation, especially related to charts or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Datuak

-0.90

 незавершена

-0.89

 <<<<<<<<<<<<<<

-0.89

Geplaatst

-0.86

 itſelf

-0.86

 Meksiku

-0.85

 myſelf

-0.85

المناصب

-0.81

 שוליים

-0.80

 themſelves

-0.79

POSITIVE LOGITS

addComponent

0.52

0.47

osin

0.45

 auto

0.44

hor

0.42

sho

0.42

PLACE

0.41

غير

0.41

<strong>

0.41

iki

0.40

Activations Density 0.501%

references to data presentation, especially related to charts or figures

No Comments

No Known Activations