INDEX

Explanations

references to entertainment topics or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

InSection

-0.84

idopsis

-0.84

 AssemblyCulture

-0.82

QLabel

-0.79

DataSnapshot

-0.77

 Dernière

-0.75

 Koval

-0.74

 Rojas

-0.73

 utilisons

-0.71

Virgo

-0.70

POSITIVE LOGITS

 entertainment

1.53

 entertained

1.37

 entertain

1.27

 entertaining

1.26

Entertainment

1.23

 Entertainment

1.23

entertainment

1.18

 entertainments

1.16

 ENTERTAINMENT

1.02

 ―――――

1.01

Activations Density 0.067%

references to entertainment topics or sources

No Comments

No Known Activations