INDEX

Explanations

expressions of uncertainty or doubt

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

cendental

-0.63

 ELEV

-0.61

RegressionTest

-0.59

MultipartFile

-0.56

indrome

-0.56

IGraphics

-0.55

 Horowitz

-0.54

gdx

-0.54

 Ayala

-0.54

Zeneca

-0.54

POSITIVE LOGITS

 unsure

1.21

 Uncertain

0.95

Wondering

0.83

 uncertain

0.83

 unclear

0.82

 doubting

0.82

 sure

0.79

 doubt

0.76

 duda

0.76

HasForeignKey

0.76

Activations Density 0.061%

expressions of uncertainty or doubt

No Comments

No Known Activations