INDEX

Explanations

terms related to health and medical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

NOPQRST

-0.97

حوالہ

-0.77

Климат

-0.73

 RoutedEventArgs

-0.71

Hozzáférés

-0.69

otheses

-0.66

TintMode

-0.66

Przypisy

-0.65

Obrázky

-0.65

FormTagHelper

-0.64

POSITIVE LOGITS

or

0.93

any

0.86

 oder

0.79

 vagy

0.74

 или

0.73

 atau

0.72

 eller

0.71

 otherwise

0.69

それとも

0.67

 หรือ

0.66

Activations Density 0.706%

terms related to health and medical processes

No Comments

No Known Activations