INDEX

Explanations

occurrences of character names and their evaluations in film reviews

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Negative Logits

ModelSerializer

-0.54

الدراسه

-0.49

 مشين

-0.48

ReusableCell

-0.45

nloa

-0.44

jamientos

-0.42

 utafitiHapana

-0.41

rungsseite

-0.41

 DbSet

-0.40

extAlignment

-0.40

POSITIVE LOGITS

 nahilalakip

0.47

 Grau

0.44

 Sonn

0.42

providedIn

0.41

Rel

0.40

InputElement

0.37

 unfavourable

0.36

 Sonne

0.36

 existi

0.35

Reg

0.35

Activations Density 0.162%

occurrences of character names and their evaluations in film reviews

No Known Activations