INDEX

Explanations

terms related to possession and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 possess

-2.06

 possession

-2.02

 possessed

-1.87

 possesses

-1.77

Poss

-1.70

possession

-1.70

 possessing

-1.66

 Possession

-1.59

 posses

-1.53

poss

-1.46

POSITIVE LOGITS

kháu

0.73

 pyplot

0.68

DebuggerStep

0.64

例句

0.61

 resourceCulture

0.61

PointerException

0.60

rrggbb

0.60

WEBPACK

0.59

IntoConstraints

0.59

EMPLOYMENT

0.58

Activations Density 0.257%

terms related to possession and ownership

No Comments

No Known Activations