INDEX

Explanations

references to payloads in a programming context, particularly within data structures or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

PerformLayout

-0.65

WithIOException

-0.52

ientí

-0.51

buttonBar

-0.50

 martyrdom

-0.49

 Scher

-0.49

évaluateur

-0.48

IBOutlet

-0.48

setConfig

-0.48

发表于

-0.48

POSITIVE LOGITS

 coordinates

0.96

 Coordinator

0.94

 coordinator

0.91

 Mall

0.90

 mall

0.88

 Coordinates

0.87

coordinates

0.86

 COORDIN

0.79

Mall

0.78

 coordinators

0.77

Activations Density 0.045%

references to payloads in a programming context, particularly within data structures or functions

No Comments

No Known Activations