INDEX

Explanations

comparative phrases and expressions indicating similarity or equality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 isolation

-0.45

疏

-0.44

FailureListener

-0.44

 وتسجيلات

-0.43

 authority

-0.43

 gaps

-0.43

 Authority

-0.43

 Details

-0.43

 Draft

-0.43

entieth

-0.42

POSITIVE LOGITS

DrawerToggle

0.75

 equal

0.68

equal

0.68

 igual

0.68

 parfaite

0.67

 Equal

0.66

mybatisplus

0.65

 FetchType

0.65

featureID

0.64

 igualdad

0.63

Activations Density 0.501%

comparative phrases and expressions indicating similarity or equality

No Comments

No Known Activations