INDEX

Explanations

phrases and terms related to special cases or subsets within a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.69

BagConstraints

-0.67

 دیکھیے

-0.67

GoogleApiClient

-0.67

makeConstraints

-0.65

}`).

-0.65

下载附件

-0.63

клопе

-0.61

 useAppContext

-0.60

 Normdatei

-0.60

POSITIVE LOGITS

 variant

0.74

 component

0.73

 version

0.68

 componente

0.67

component

0.65

 extension

0.64

 Component

0.62

 form

0.60

 subset

0.59

 variants

0.59

Activations Density 0.653%

phrases and terms related to special cases or subsets within a given context

No Comments

No Known Activations