INDEX

Explanations

terms related to medical and biological data, especially those involving analyses and categorizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

haviour

-0.72

erapeutic

-0.65

iffance

-0.62

avelength

-0.61

tifacts

-0.60

ipheral

-0.59

ifolium

-0.59

 ویکی‌پدیا

-0.59

 rispet

-0.59

pecified

-0.58

POSITIVE LOGITS

 estekak

0.96

PreferredItem

0.94

AndEndTag

0.92

MessageTagHelper

0.92

expandindo

0.87

Хьажоргаш

0.81

ftagPool

0.75

+#+#

0.74

 للمعارف

0.73

Personensuche

0.71

Activations Density 4.834%

terms related to medical and biological data, especially those involving analyses and categorizations

No Comments

No Known Activations