INDEX

Explanations

references to tree structures and the term "Tree" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 pener

-0.35

 consectetur

-0.33

 préférences

-0.31

 يتيمه

-0.31

 colega

-0.29

 fuck

-0.29

 itinéraire

-0.28

FunctionFlags

-0.28

 cabin

-0.28

 knex

-0.28

POSITIVE LOGITS

Tree

1.65

tree

1.49

 Tree

1.45

TREE

1.30

 tree

1.26

 TREE

1.19

ree

1.06

ツリー

0.99

REE

0.89

TreeNode

0.88

Activations Density 0.054%

references to tree structures and the term "Tree" in various contexts

No Known Activations