INDEX

Explanations

patterns related to data formatting or coding structures

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

Unicode characters and encodings

np_acts-logits-general · gemini-2.0-flash

unicode escape sequences

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

DECREF

-0.59

BeginInit

-0.59

AccessorTable

-0.55

ftagPool

-0.54

rxjs

-0.53

########.

-0.52

----</

-0.51

ocardial

-0.51

таратура

-0.51

Enllaces

-0.50

POSITIVE LOGITS

 Unicode

0.70

Unicode

0.61

 unicode

0.55

 encoding

0.55

 emojis

0.54

躇

0.54

conversions

0.54

 emoji

0.53

igus

0.52

CJK

0.52

Activations Density 1.343%

patterns related to data formatting or coding structures

Unicode characters and encodings

unicode escape sequences

No Comments

No Known Activations