INDEX

Explanations

phrases involving capabilities, possibilities, and behaviors related to actions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Reine

-0.58

 froide

-0.55

 Otero

-0.55

Cold

-0.54

 Languedoc

-0.52

 Cold

-0.52

cold

-0.52

 Genova

-0.52

 onStop

-0.51

ourcen

-0.51

POSITIVE LOGITS

MigrationBuilder

0.76

TagMode

0.63

]]

0.62

RegistryLite

0.61

HideFlags

0.60

 able

0.60

prüche

0.58

ContentAsync

0.58

codable

0.57

kaar

0.57

Activations Density 0.157%

phrases involving capabilities, possibilities, and behaviors related to actions or conditions

No Comments

No Known Activations