INDEX

Explanations

code-related keywords and structure that indicate testing and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

sizeCache

-0.53

ophi

-0.53

Geplaatst

-0.52

oph

-0.52

()?;

-0.50

ācija

-0.49

țion

-0.48

robi

-0.48

 للاسماء

-0.48

_));

-0.48

POSITIVE LOGITS

 ویکی‌پدیای

0.54

destroyAll

0.52

原始内容存档于

0.51

batore

0.51

ayaquil

0.51

 femoral

0.50

 bander

0.48

Bibliograf

0.47

ssid

0.46

 Sarmiento

0.46

Activations Density 0.113%

code-related keywords and structure that indicate testing and function definitions

No Comments

No Known Activations