INDEX

Explanations

terms related to programming libraries and system components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 kasarigan

-0.77

#![

-0.68

躇

-0.64

__(/*!

-0.61

<bos>

-0.60

addPreferredGap

-0.58

addContainerGap

-0.58

addGap

-0.58

佗

-0.57

rrggbb

-0.56

POSITIVE LOGITS

contentLoaded

0.89

MessageOf

0.81

ollectionView

0.72

stateProvider

0.71

 springfox

0.57

PickerController

0.57

redux

0.55

omitempty

0.54

 ProtoMessage

0.54

ngrx

0.54

Activations Density 0.587%

terms related to programming libraries and system components

No Comments

No Known Activations