INDEX

Explanations

TODO comments and markers indicating further tasks or changes needed in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 BoxDecoration

-0.82

HasAnnotation

-0.70

UIControlState

-0.67

Hentet

-0.67

исленность

-0.67

InstanceState

-0.65

 saites

-0.62

="#"><

-0.61

classnames

-0.61

IANGLES

-0.61

POSITIVE LOGITS

 removed

0.83

 need

0.82

fix

0.81

 commented

0.81

 refactor

0.76

 remove

0.75

 Removed

0.74

 Need

0.74

 Needs

0.73

commented

0.73

Activations Density 0.384%

TODO comments and markers indicating further tasks or changes needed in the code

No Comments

No Known Activations