INDEX

Explanations

sections in a structured document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-0.99

 BoxFit

-0.83

 Italijani

-0.78

 Baillargeon

-0.77

 Freuden

-0.76

 transfieras

-0.74

uxxxx

-0.73

 BorderRadius

-0.72

 layui

-0.71

хьтан

-0.69

POSITIVE LOGITS

section

2.52

sections

1.46

subsubsection

1.42

 section

1.41

Section

1.36

subsection

1.30

 sections

1.28

SECTION

1.27

 Sections

1.24

 Section

1.21

Activations Density 0.015%

sections in a structured document

No Comments

No Known Activations