INDEX

Explanations

references to actors and their roles in film or television

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

 atap

-0.31

att

-0.31

面上

-0.30

 vekt

-0.30

 ancienne

-0.30

 excepcional

-0.29

 efectivo

-0.28

 fallas

-0.28

 attiva

-0.28

 absolument

-0.28

POSITIVE LOGITS

 EconPapers

0.77

تقاوى

0.70

 defaultstate

0.64

 noDo

0.63

DockStyle

0.62

Personendaten

0.62

⤹

0.62

LookAnd

0.60

jsonwebtoken

0.60

 autorytatywna

0.58

Activations Density 0.141%

references to actors and their roles in film or television

No Comments

No Known Activations