INDEX

Explanations

HTML tags in a document

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

html tags

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 resourceCulture

-1.19

 NSCoder

-1.17

WriteTagHelper

-1.13

ValueStyle

-1.12

AddTagHelper

-1.10

 الرياضيه

-1.09

 يتيمه

-1.04

StructEnd

-1.04

AndEndTag

-1.03

principalColumn

-1.01

POSITIVE LOGITS

↵↵

0.42

<h1>

0.42

0.41

/*

0.40

↵↵↵

0.38

<b>

0.37

The

0.36

Activations Density 0.011%

HTML tags in a document

html tags

No Comments

No Known Activations