INDEX

Explanations

hierarchical structures in 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 repur

-0.42

arden

-0.41

ecap

-0.41

 createState

-0.40

PerPage

-0.40

泊

-0.40

flashdata

-0.39

xtext

-0.39

iolo

-0.38

 preen

-0.37

POSITIVE LOGITS

 tree

1.25

 recursively

1.19

 Tree

1.17

Tree

1.14

 TREE

1.13

tree

1.09

 recursive

1.07

 hierarchy

1.06

 recursion

1.04

 trees

1.04

Activations Density 0.999%

hierarchical structures in data representation

No Comments

No Known Activations