INDEX

Explanations

structured formatting elements in a code or data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

VIAF

-0.71

JpaRepository

-0.70

DockStyle

-0.68

ChromeDriver

-0.63

 grpc

-0.62

moveToFirst

-0.61

 dobbiamo

-0.60

 Normdatei

-0.59

لاثة

-0.58

íí

-0.57

POSITIVE LOGITS

__

1.16

 Lank

0.63

abestanden

0.59

 CreateTagHelper

0.53

ाहरण

0.53

obod

0.53

__,

0.52

 lice

0.52

})}$

0.52

LikeLike

0.52

Activations Density 0.080%

structured formatting elements in a code or data context

No Comments

No Known Activations