INDEX

Explanations

references to alternatives or additional options

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

 lainnya

-0.78

 الأخرى

-0.67

tidaknya

-0.65

 berikutnya

-0.64

setupUi

-0.63

 andern

-0.63

AddTagHelper

-0.62

 restantes

-0.61

 JSTOR

-0.60

 autre

-0.60

POSITIVE LOGITS

worldly

1.54

 than

1.23

than

0.93

Than

0.89

 niż

0.87

 THAN

0.80

world

0.78

था

0.77

 similar

0.74

wiſe

0.72

Activations Density 0.119%

references to alternatives or additional options

No Comments

No Known Activations