INDEX

Explanations

references to missing persons or individuals who are unaccounted for

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 برانيه

-0.51

DataAnnotations

-0.43

芝

-0.43

MOC

-0.42

xed

-0.41

corns

-0.40

 snippetHide

-0.40

Carr

-0.40

auce

-0.39

 insi

-0.39

POSITIVE LOGITS

 disappeared

0.70

 disappearance

0.69

 disambiguazione

0.65

 disappear

0.63

 disparition

0.61

 disappears

0.59

 disparu

0.58

 vanished

0.57

Gone

0.56

 desaparecido

0.56

Activations Density 0.260%

references to missing persons or individuals who are unaccounted for

No Comments

No Known Activations