INDEX

Explanations

references to formatting and protocol structures in data

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

"format" followed by a colon

np_acts-logits-general · gemini-2.0-flash

format and its value

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

abestanden

-0.89

 calculées

-0.82

 autorytatywna

-0.80

Související

-0.79

AnchorTagHelper

-0.78

webElementXpaths

-0.77

jspx

-0.74

onViewCreated

-0.74

requestCode

-0.72

FieldBuilder

-0.71

POSITIVE LOGITS

 FORMAT

1.26

 formats

1.20

 Format

1.14

 format

1.10

 Formats

1.09

format

1.09

formats

1.03

FORMAT

1.02

Formats

1.01

Format

0.99

Activations Density 0.210%

references to formatting and protocol structures in data

"format" followed by a colon

format and its value

No Comments

No Known Activations