INDEX

Explanations

internet-related terms and numerical sequences

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

domain names and IPs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

ConstraintMaker

-0.76

OGND

-0.74

 >=",

-0.72

AddTagHelper

-0.66

IsContent

-0.66

:+:

-0.66

WireFormatLite

-0.65

脚注の使い方

-0.65

TagHelpers

-0.65

 "..\..\..\

-0.63

POSITIVE LOGITS

 domínio

0.48

 Internet

0.46

 subnet

0.45

系

0.44

 होते

0.43

 diku

0.43

 domain

0.41

 internet

0.41

帯

0.41

 dominio

0.40

Activations Density 0.116%

internet-related terms and numerical sequences

domain names and IPs

No Comments

No Known Activations