INDEX

Explanations

high numerical values and patterns related to data representation

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

Numerical strings

np_acts-logits-general · gemini-2.0-flash

words ending in ol

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

AddTagHelper

-0.89

contentLoaded

-0.81

Tembelea

-0.73

 doInBackground

-0.73

 createState

-0.73

ContentAsync

-0.71

 CreateTagHelper

-0.71

 defaultstate

-0.71

 مشين

-0.70

 AssemblyTitle

-0.69

POSITIVE LOGITS

<bos>

0.68

asdf

0.47

 rangka

0.43

phazard

0.43

qwerty

0.42

DE

0.41

ỏ

0.41

abcd

0.40

 Sociale

0.40

百科

0.38

Activations Density 0.478%

high numerical values and patterns related to data representation

Numerical strings

words ending in ol

No Comments

No Known Activations