INDEX

Explanations

references to turnover in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

 ProtoMessage

-0.73

Хьажоргаш

-0.65

Искәрмәләр

-0.59

 doPost

-0.58

XmlAccessType

-0.58

GOTREF

-0.58

 дописавши

-0.57

Traceback

-0.56

hasMoreElements

-0.55

Kanpo

-0.54

POSITIVE LOGITS

Aware

0.75

Set

0.68

 متعلقه

0.65

aware

0.64

sig

0.64

 turnovers

0.63

DockStyle

0.61

SIG

0.61

Turn

0.60

Sig

0.60

Activations Density 0.043%

references to turnover in various contexts

No Comments

No Known Activations