INDEX

Explanations

abbreviations and acronyms related to organizations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 itſelf

-0.74

 againſt

-0.71

 myſelf

-0.63

AnchorStyles

-0.59

 Ανακτήθηκε

-0.57

UrlResolution

-0.55

Παραπομπές

-0.54

HomeAsUpEnabled

-0.52

 faſt

-0.52

 finally

-0.51

POSITIVE LOGITS

 nakalista

0.78

0.71

0.68

wpi

0.67

0.65

nvarchar

0.65

0.64

Activations Density 0.641%

abbreviations and acronyms related to organizations and entities

No Comments

No Known Activations