INDEX

Explanations

HTML or XML markup elements and tags

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

HTML bold tags and bracketed expressions

np_acts-logits-general · gemini-2.0-flash

special characters denoting markup

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 CreateTagHelper

-0.79

fjspx

-0.76

 ModelExpression

-0.63

SequentialGroup

-0.63

oneofs

-0.59

例文帳に追加

-0.58

</tr>

-0.56

 ***!

-0.56

GEBURTSDATUM

-0.55

messageInfo

-0.55

POSITIVE LOGITS

 itſelf

1.21

 myſelf

1.13

 Houſe

1.13

 Majefty

1.06

 Jefus

1.06

ſelf

1.04

 pleaſure

1.03

 faſt

1.03

 himſelf

0.99

 Monfieur

0.98

Activations Density 0.413%

HTML or XML markup elements and tags

HTML bold tags and bracketed expressions

special characters denoting markup

No Comments

No Known Activations