INDEX

Explanations

terms related to precision and exactness in definitions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-0.70

 esternos

-0.65

adaptiveStyles

-0.62

ilever

-0.60

 informée

-0.59

 koszulka

-0.59

 indígen

-0.58

Manbalar

-0.57

pompa

-0.57

 bershka

-0.57

POSITIVE LOGITS

precise

0.95

 precisely

0.91

 precise

0.88

 exact

0.87

 EXACT

0.86

 Precise

0.85

exact

0.84

 exac

0.83

Precise

0.83

 exactly

0.81

Activations Density 0.273%

terms related to precision and exactness in definitions or descriptions

No Comments

No Known Activations