INDEX

Explanations

XML elements or tags, specifically focusing on names and error codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

+#+#

-0.96

sizeCache

-0.68

AndEndTag

-0.64

 виправивши

-0.62

transQ

-0.61

AsUp

-0.61

XmlAccessorType

-0.59

 <>",

-0.59

 թվական

-0.57

 ""],

-0.57

POSITIVE LOGITS

The

0.50

We

0.44

 mukaan

0.43

Base

0.41

source

0.40

방

0.39

If

0.39

Piece

0.37

Connect

0.37

General

0.37

Activations Density 0.021%

XML elements or tags, specifically focusing on names and error codes

No Comments

No Known Activations