INDEX

Explanations

references to academic publishers and their associated locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

/**

-0.47

 calore

-0.46

更多

-0.44

 bezeichneter

-0.43

 qualcosa

-0.43

 dramatique

-0.42

 ujednoznacz

-0.42

reportWebVitals

-0.40

tions

-0.40

 oggetto

-0.39

POSITIVE LOGITS

 kasarigan

0.81

Gambas

0.74

hoeddwyd

0.73

 '\\;'

0.70

 Roskov

0.70

 Signalez

0.69

KURZBESCHREIBUNG

0.68

 Infórmanos

0.68

Gön

0.65

 LoggerFactory

0.65

Activations Density 0.494%

references to academic publishers and their associated locations

No Comments

No Known Activations