INDEX

Explanations

references to questions and uncertainties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Démographie

-0.56

OptionsMenu

-0.51

webElementXpaths

-0.50

 Became

-0.49

Become

-0.49

ArrowToggle

-0.48

DeleteBehavior

-0.48

IntoConstraints

-0.47

Atoi

-0.47

OrNil

-0.45

POSITIVE LOGITS

 having

1.94

 have

1.79

 Having

1.68

having

1.66

Having

1.64

 memiliki

1.62

 Have

1.56

had

1.55

have

1.53

Have

1.52

Activations Density 1.216%

references to questions and uncertainties

No Comments

No Known Activations