INDEX

Explanations

mathematical labels or references in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

//{

-0.64

 télécharge

-0.64

</tfoot>

-0.63

CodedInputStream

-0.62

 Souha

-0.59

 avoient

-0.59

andescent

-0.58

copg

-0.58

glasses

-0.58

 cdti

-0.57

POSITIVE LOGITS

addComponent

0.72

 common

0.45

IConfiguration

0.44

ฉ

0.44

nitzer

0.44

ضل

0.44

off

0.44

 through

0.43

TagHelper

0.43

ome

0.42

Activations Density 0.117%

mathematical labels or references in a document

No Comments

No Known Activations