INDEX

Explanations

mathematical notations and expressions, particularly involving parentheses and braces

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

babkan

-0.66

hangi

-0.65

InputTagHelper

-0.64

invokeLater

-0.62

dames

-0.61

الحياه

-0.61

addEdge

-0.60

 consolidated

-0.58

meist

-0.58

 AppComponent

-0.57

POSITIVE LOGITS

LL

0.84

Tor

0.74

Tor

0.66

LL

0.64

ymce

0.58

LikeLike

0.58

SequentialGroup

0.55

Not

0.54

Shelter

0.54

}{\

0.53

Activations Density 0.164%

mathematical notations and expressions, particularly involving parentheses and braces

No Comments

No Known Activations