INDEX

Explanations

clear instructions and steps related to processes or tools

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

 resourceCulture

-0.83

Quo

-0.65

 useDispatch

-0.62

 مرئيه

-0.62

 TextInputType

-0.60

IBarButtonItem

-0.59

 joaat

-0.57

shadowRadius

-0.55

artifactId

-0.54

想想

-0.53

POSITIVE LOGITS

 instructions

2.18

 instruction

1.85

instructions

1.82

 Instructions

1.81

 guide

1.70

Instructions

1.69

 step

1.69

 directions

1.66

 steps

1.62

 INSTRUCTIONS

1.62

Activations Density 0.352%

clear instructions and steps related to processes or tools

No Comments

No Known Activations