INDEX

Explanations

references to document-related elements in code or technical writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

MessageTagHelper

-0.85

PerformLayout

-0.82

 noqa

-0.80

layoutControl

-0.75

 Jefus

-0.73

RegressionTest

-0.72

ContentAlignment

-0.72

msgTypes

-0.71

 himſelf

-0.70

ChrTalk

-0.70

POSITIVE LOGITS

#+#

1.64

بوابة

1.55

Portail

1.31

RestController

1.00

nestjs

0.99

:+:

0.93

 StatelessWidget

0.91

########.

0.84

Portale

0.72

 viewDidLoad

0.71

Activations Density 0.002%

references to document-related elements in code or technical writing

No Comments

No Known Activations