INDEX

Explanations

structured markup or HTML elements in a document

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

HTML tags and attributes

np_acts-logits-general · gemini-2.0-flash

HTML-like structures and code

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 queſta

-1.06

 ſind

-1.02

 NSCoder

-0.92

$_"

-0.91

parsedMessage

-0.91

 ſche

-0.88

ſicht

-0.88

 Infórmanos

-0.88

ésultats

-0.88

inSlope

-0.87

POSITIVE LOGITS

0.41

0.34

 layout

0.32

layout

0.30

0.29

 open

0.29

 Tief

0.28

 style

0.27

Activations Density 0.200%

structured markup or HTML elements in a document

HTML tags and attributes

HTML-like structures and code

No Comments

No Known Activations