INDEX

Explanations

technical terminology related to programming and scientific measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 skla

-0.57

زار

-0.54

brin

-0.54

 Foxy

-0.54

 Aufs

-0.53

Искәрмәләр

-0.53

endurch

-0.52

 McCarty

-0.52

‌پ

-0.52

rophoresis

-0.51

POSITIVE LOGITS

 Meksiku

0.66

 Provision

0.66

NegativeButton

0.66

Provision

0.63

insee

0.63

AddTagHelper

0.62

 asym

0.62

provision

0.61

 provisioning

0.60

 provision

0.58

Activations Density 2.713%

technical terminology related to programming and scientific measurements

No Comments

No Known Activations