INDEX

Explanations

annotations and configuration settings within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

المشاركات

-0.52

-0.43

ugc

-0.43

 vedette

-0.42

كويكب

-0.42

 intptr

-0.41

 Recife

-0.40

 parrots

-0.39

 Pernambuco

-0.39

 turno

-0.39

POSITIVE LOGITS

Datuak

0.86

__":

0.84

__':

0.76

Personendaten

0.73

 bezeichneter

0.73

CloseOperation

0.72

 kaarangay

0.71

Portale

0.71

 nakalista

0.69

tagHelperRunner

0.69

Activations Density 0.029%

annotations and configuration settings within code

No Comments

No Known Activations