INDEX

Explanations

references to data files and tables within the document

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

Information presented in tables

np_acts-logits-general · gemini-2.0-flash

tables contain lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WebVitals

-0.65

 jLabel

-0.64

!*\

-0.58

esModule

-0.57

tagHelperRunner

-0.57

](#

-0.56

webElementGuid

-0.55

 farlo

-0.55

УДК

-0.55

VersionUID

-0.55

POSITIVE LOGITS

 containing

1.23

 contains

1.21

 contain

1.08

containing

1.03

 represents

0.99

 representing

0.98

 Containing

0.98

 Contains

0.98

contains

0.97

 contenant

0.93

Activations Density 0.880%

references to data files and tables within the document

Information presented in tables

tables contain lists

No Comments

No Known Activations