INDEX

Explanations

references to product specifications and features

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

raszamy

-0.51

ütfen

-0.50

 decorativos

-0.48

 profesión

-0.47

VIAF

-0.46

 abstrait

-0.45

 Boud

-0.44

 quidem

-0.44

 متعلقه

-0.42

gatsby

-0.41

POSITIVE LOGITS

 smartphone

1.00

 smartphones

0.99

 hardware

0.96

 Android

0.94

 phones

0.92

 handset

0.89

 device

0.88

 Samsung

0.88

 Nokia

0.87

 Xiaomi

0.85

Activations Density 0.352%

references to product specifications and features

No Comments

No Known Activations