INDEX

Explanations

mentions of "best" along with comparative phrases related to evaluation or selection

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

"best" followed by other words

np_acts-logits-general · gemini-2.0-flash

best followed by a noun

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 فريبيس

-0.76

OGND

-0.75

 AssemblyTitle

-0.74

 يتيمه

-0.74

crumbs

-0.72

 оригіналу

-0.71

 BoxDecoration

-0.71

ragalactic

-0.70

 Obrador

-0.69

 Biôgrafia

-0.69

POSITIVE LOGITS

 BEST

1.06

BEST

0.99

 Best

0.96

 best

0.87

Best

0.86

best

0.83

 suited

0.82

sellers

0.71

 possible

0.69

selling

0.67

Activations Density 0.126%

mentions of "best" along with comparative phrases related to evaluation or selection

"best" followed by other words

best followed by a noun

No Comments

No Known Activations