INDEX

Explanations

statistical data and numerical values related to clinical findings

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

counts of patients/genes/samples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 nakalista

-0.40

addLast

-0.36

 Einblick

-0.35

一段

-0.34

lichung

-0.34

 istore

-0.32

发表于

-0.31

ulah

-0.31

GeoNames

-0.31

زاد

-0.31

POSITIVE LOGITS

 autorytatywna

0.55

 précédente

0.54

 coscienza

0.52

 betweenstory

0.49

########.

0.47

RTEX

0.47

 vectorielle

0.47

rictions

0.46

 EconPapers

0.46

期刊论文

0.45

Activations Density 0.043%

statistical data and numerical values related to clinical findings

counts of patients/genes/samples

No Comments

No Known Activations