INDEX

Explanations

elements related to data structure definitions and tree nodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AutoField

-0.57

ecap

-0.56

 ويكيپيديا

-0.47

messageInfo

-0.46

 tấm

-0.45

 forState

-0.44

@"/

-0.42

CppMethod

-0.42

WireFormatLite

-0.41

 repur

-0.41

POSITIVE LOGITS

 subtree

1.42

 tree

1.40

 Tree

1.30

 parent

1.29

Tree

1.26

 children

1.24

 TREE

1.23

 recursively

1.21

tree

1.19

 child

1.19

Activations Density 0.721%

elements related to data structure definitions and tree nodes

No Comments

No Known Activations