INDEX

Explanations

terms and references related to trees and tree structures in programming and data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.39

 Monfieur

-1.39

 pleaſure

-1.31

 themſelves

-1.27

 ſeveral

-1.27

Efq

-1.26

 himſelf

-1.25

 greateſt

-1.23

 auffi

-1.22

Eſ

-1.22

POSITIVE LOGITS

 tree

2.38

 Tree

2.26

 TREE

2.09

Tree

2.04

 trees

2.02

tree

2.00

 Trees

1.85

TREE

1.78

Trees

1.67

trees

1.53

Activations Density 0.040%

terms and references related to trees and tree structures in programming and data representation

No Comments

No Known Activations