INDEX

Explanations

structured data and definitions related to API specifications and code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

↵↵

-0.77

)))),

-0.63

 iaitu

-0.58

 निम्नलिखित

-0.55

 https

-0.55

 suivante

-0.54

<bos>

-0.52

↵

-0.52

 następujące

-0.52

「

-0.50

POSITIVE LOGITS

GEBURTSDATUM

1.07

 الحره

1.05

 للمعارف

0.93

GraphicsUnit

0.93

KommentareTeilen

0.89

 дописавши

0.87

Hentet

0.86

AsUp

0.84

 الرياضيه

0.83

+#+#

0.80

Activations Density 0.630%

structured data and definitions related to API specifications and code structures

No Comments

No Known Activations