INDEX

Explanations

references to guest appearances or guest contributors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Norris

-0.65

 malpractice

-0.62

ols

-0.62

Toolbox

-0.61

 Dickerson

-0.60

Toolkit

-0.59

highway

-0.58

 crippling

-0.57

 Moriarty

-0.57

 Whittaker

-0.57

POSITIVE LOGITS

 guest

2.58

 guests

2.48

 Guests

2.46

 GUEST

2.46

 Guest

2.46

Guest

2.36

Guests

2.36

guest

2.34

GUEST

2.34

guests

2.18

Activations Density 0.040%

references to guest appearances or guest contributors in various contexts

No Comments

No Known Activations