INDEX

Explanations

terms related to scientific observations and data documentation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aarrggbb

-0.60

instancetype

-0.56

Portály

-0.47

 disambiguazione

-0.46

ecm

-0.46

 HasFactory

-0.45

 IndexPath

-0.45

GEBURTSDATUM

-0.44

 wireType

-0.44

lickr

-0.43

POSITIVE LOGITS

 diverti

0.39

 participa

0.37

ciety

0.37

 Signalez

0.37

Cadastrar

0.36

rmtree

0.36

 Descubre

0.35

눠

0.35

WEBPACK

0.34

gestellten

0.34

Activations Density 0.734%

terms related to scientific observations and data documentation

No Known Activations