INDEX

Explanations

terms related to margin and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__":

-0.67

yntaxException

-0.66

 correctes

-0.65

 للمعارف

-0.62

featureID

-0.62

findpost

-0.62

 AssemblyCulture

-0.60

RegistryLite

-0.59

 flare

-0.58

__':

-0.57

POSITIVE LOGITS

 margin

1.72

margin

1.47

 Margin

1.46

Margin

1.38

 margins

1.25

 excess

1.06

excess

1.05

Excess

1.04

 Excess

1.04

 marginal

0.96

Activations Density 0.081%

terms related to margin and its variations in different contexts

No Comments

No Known Activations