INDEX

Explanations

elements describing physical characteristics or traits

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

 potentially

-0.59

orszá

-0.56

 kita

-0.55

potentially

-0.51

 ours

-0.50

要么

-0.48

在本

-0.48

будь

-0.47

 arguably

-0.46

能在

-0.46

POSITIVE LOGITS

 suddenly

1.03

 Suddenly

0.94

Suddenly

0.90

suddenly

0.88

 thereupon

0.87

 aussitôt

0.83

 whereupon

0.80

 forthwith

0.80

 soudain

0.78

 immediately

0.75

Activations Density 0.223%

elements describing physical characteristics or traits

No Comments

No Known Activations