INDEX

Explanations

phrases that express relationships or dependencies between concepts

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

بخش

-0.44

frontmatter

-0.43

 Lengkap

-0.40

 None

-0.40

Other

-0.39

None

-0.39

ay

-0.39

szönöm

-0.38

zda

-0.37

POSITIVE LOGITS

ReusableCell

0.88

IndentedString

0.86

 Wikimedijinoj

0.85

帖最后由

0.83

fromnode

0.83

TagMode

0.82

GraphicsUnit

0.81

enumi

0.81

 متعلقه

0.80

Дереккөздер

0.79

Activations Density 0.214%

phrases that express relationships or dependencies between concepts

No Comments

No Known Activations