INDEX

Explanations

metrics and statistics related to film reviews and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 insegn

-0.54

__.__

-0.52

 sélectionnés

-0.51

sieht

-0.51

ätzliche

-0.50

Specify

-0.49

 paraît

-0.49

romycin

-0.49

 hygien

-0.48

ROUTINE

-0.48

POSITIVE LOGITS

verwijspagina

0.76

 kasarigan

0.71

ValueStyle

0.66

\}\\

0.62

DataAnnotations

0.61

 }}$}

0.60

 خارجية

0.58

 outright

0.58

homonymie

0.58

 skru

0.58

Activations Density 0.358%

metrics and statistics related to film reviews and performance

No Comments

No Known Activations