INDEX

Explanations

elements related to logical or mathematical expressions and coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.51

-0.50

-0.48

 volont

-0.47

httphttps

-0.47

ordinaire

-0.47

-0.44

 communautaire

-0.43

 garde

-0.43

POSITIVE LOGITS

 Signalez

0.86

 bezeichneter

0.85

 Majefty

0.83

انيف

0.82

Jereo

0.81

TestingModule

0.80

ArgsConstructor

0.79

oa̍t

0.78

 onCancelled

0.76

 Normdatei

0.73

Activations Density 1.485%

elements related to logical or mathematical expressions and coding syntax

No Comments

No Known Activations