INDEX

Explanations

references to changes in mathematical or coding parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-1.11

 estekak

-1.07

 <>",

-0.99

 تضيفلها

-0.98

Datuak

-0.96

GeoNames

-0.94

تقاوى

-0.92

 lenker

-0.90

 linkovi

-0.89

NewUrlParser

-0.89

POSITIVE LOGITS

↵↵

0.68

0.59

The

0.57

<h2>

0.50

↵↵↵↵

0.47

Or

0.46

icola

0.46

などなど

0.46

Activations Density 0.475%

references to changes in mathematical or coding parameters

No Comments

No Known Activations