INDEX

Explanations

references to books

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

nabis

-0.68

NegativeButton

-0.68

UseVisualStyle

-0.66

RTHOOK

-0.61

cloudflare

-0.56

 McFar

-0.56

ParallelGroup

-0.56

Ỉ

-0.56

 hilsen

-0.55

 Weiden

-0.55

POSITIVE LOGITS

 book

4.38

 Book

4.36

Book

4.25

book

4.17

 BOOK

3.90

BOOK

3.77

books

3.26

 books

3.25

 Books

3.09

Books

2.95

Activations Density 0.059%

references to books

No Comments

No Known Activations