INDEX

Explanations

references to blades and their specific characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 pull

-0.61

RectangleBorder

-0.54

Bag

-0.54

 matter

-0.53

sou

-0.53

pin

-0.51

gri

-0.51

 knock

-0.49

Big

-0.48

it

-0.48

POSITIVE LOGITS

 blade

1.06

blade

0.99

 Blade

0.89

 blades

0.88

blades

0.87

Blade

0.85

 Blades

0.84

 leçon

0.80

 <=",

0.80

 Wiktionnaire

0.77

Activations Density 0.113%

references to blades and their specific characteristics

No Comments

No Known Activations