INDEX

Explanations

instances of the word "where" and mathematical symbols used in definitions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 فريبيس

-0.66

Pull

-0.56

enumii

-0.55

pull

-0.53

iritual

-0.52

AsUp

-0.51

TUR

-0.49

 Ikke

-0.49

 imgs

-0.49

Ikke

-0.49

POSITIVE LOGITS

 للاسماء

0.85

 surla

0.84

Sklici

0.82

URLException

0.81

AddHtmlAttribute

0.77

QMetaType

0.76

makeConstraints

0.73

where

0.73

 <<<<<<<<<<<<<<

0.72

useNewUrlParser

0.71

Activations Density 0.398%

instances of the word "where" and mathematical symbols used in definitions or conditions

No Comments

No Known Activations