INDEX

Explanations

keywords related to efficiency and performance metrics 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 незавершена

-0.61

Væ

-0.56

 Daß

-0.51

 Parenthood

-0.51

 GetEnumerator

-0.51

enumi

-0.51

 faune

-0.50

égard

-0.49

 tind

-0.49

Ouv

-0.49

POSITIVE LOGITS

 without

0.95

without

0.81

LookAnd

0.81

 cost

0.71

 reliably

0.71

 zonder

0.71

 без

0.69

 WITHOUT

0.69

 Without

0.69

 senza

0.69

Activations Density 0.418%

keywords related to efficiency and performance metrics in various contexts

No Comments

No Known Activations