INDEX

Explanations

symbolic representations or visual elements in the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 purpoſe

-0.79

 leaſt

-0.78

ſelves

-0.77

 uſed

-0.74

 reaſon

-0.74

 becauſe

-0.72

 greateſt

-0.71

 poffible

-0.70

 uſe

-0.70

 ſen

-0.70

POSITIVE LOGITS

.$,

0.72

 OFDb

0.71

اریخ

0.66

Tembelea

0.63

}{*}{

0.63

AnchorStyles

0.60

}{*}{}

0.58

 surla

0.57

/}

0.56

ⓧ

0.56

Activations Density 0.266%

symbolic representations or visual elements in the document

No Comments

No Known Activations