INDEX

Explanations

terms related to technical specifications and code attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 otomatig

-0.97

 surla

-0.82

EDEFAULT

-0.82

adaptiveStyles

-0.75

 CanadaChoose

-0.75

 дописавши

-0.73

 Chwiliwch

-0.73

⸮

-0.73

genodigd

-0.73

Personensuche

-0.72

POSITIVE LOGITS

 preserv

0.36

 conserv

0.36

 glor

0.35

 Hawai

0.34

 navig

0.33

 chocol

0.33

 Olymp

0.33

 sacrific

0.32

 celebr

0.32

 histor

0.32

Activations Density 0.737%

terms related to technical specifications and code attributes

No Comments

No Known Activations

terms related to technical specifications and code attributes

No Comments

No Known Activations