INDEX

Explanations

modal verbs indicating possibility or uncertainty

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

totta

-0.65

 TextAppearance

-0.64

 domestiques

-0.64

 horn

-0.61

Ehr

-0.61

Composable

-0.61

Бахар

-0.60

Armand

-0.60

ódz

-0.60

 Horn

-0.59

POSITIVE LOGITS

may

1.96

may

1.67

MAY

1.67

 might

1.59

MAY

1.58

May

1.42

might

1.38

 Might

1.34

May

1.34

Might

1.27

Activations Density 0.095%

modal verbs indicating possibility or uncertainty

No Comments

No Known Activations