INDEX

Explanations

numerical ratings and reviews related to films or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.47

 Meksiku

-0.46

PMailer

-0.41

aians

-0.41

parsedMessage

-0.41

逅

-0.41

Carp

-0.41

Gön

-0.39

__':

-0.39

__':

-0.39

POSITIVE LOGITS

 rating

0.73

Rating

0.65

 ratings

0.62

 Rating

0.57

rating

0.56

 rated

0.54

ratings

0.54

 classificação

0.54

 Ratings

0.51

 sólidos

0.51

Activations Density 0.285%

numerical ratings and reviews related to films or movies

No Comments

No Known Activations