INDEX

Explanations

references to login and account management in programming or system commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

发表于

-0.84

 CreateTagHelper

-0.83

RenderAtEndOf

-0.82

MemoryWarning

-0.76

InvalidProtocol

-0.75

 contextLoads

-0.72

 betweenstory

-0.71

LLocation

-0.71

tagHelperRunner

-0.70

 AssemblyCulture

-0.70

POSITIVE LOGITS

ⓧ

0.59

PathVariable

0.51

ั่ว

0.50

“

0.50

“

0.50

subsubsection

0.49

zheng

0.48

 Nowak

0.48

 exigences

0.47

 pair

0.47

Activations Density 0.428%

references to login and account management in programming or system commands

No Comments

No Known Activations