INDEX

Explanations

references to the concept of "best" or "optimal" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-1.04

weile

-0.74

 Drapeau

-0.73

ungeon

-0.73

Geografie

-0.71

yntaxException

-0.69

‍♀️

-0.69

etcode

-0.69

ęku

-0.68

openConnection

-0.67

POSITIVE LOGITS

 BEST

1.67

BEST

1.62

 best

1.54

best

1.54

Best

1.48

 Best

1.47

melhor

1.20

 Mejor

1.06

 beſt

1.04

better

1.01

Activations Density 0.065%

references to the concept of "best" or "optimal" in various contexts

No Comments

No Known Activations