INDEX

Explanations

sections of text representing structural or formatting patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

tagHelperRunner

-0.57

<sup>

-0.40

INDIAN

-0.35

 سكانية

-0.34

-"

-0.34

->

-0.32

 INDIAN

-0.32

...”

-0.32

..."

-0.31

 Lohan

-0.31

POSITIVE LOGITS

================

1.75

============

1.30

==============

1.29

=============

1.28

==========

1.26

===========

1.24

=========

1.23

===============

1.23

=======

1.23

========

1.23

Activations Density 0.454%

sections of text representing structural or formatting patterns

No Comments

No Known Activations