INDEX

Explanations

data and statements related to statistics and validity in analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

two

-0.56

minecraft

-0.55

 certains

-0.55

 certaines

-0.55

 more

-0.54

 algunos

-0.52

 algunas

-0.52

¿

-0.51

dik

-0.50

 alguns

-0.49

POSITIVE LOGITS

 kecuali

0.87

 sauf

0.87

 except

0.84

 excepto

0.83

Except

0.81

 Tutte

0.79

 demás

0.76

 poffible

0.75

 imaginable

0.75

 conceivable

0.74

Activations Density 0.554%

data and statements related to statistics and validity in analysis

No Comments

No Known Activations